
import pandas as pd
import numpy as np
import altair as alt
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)


customer_df = pd.read_csv('final/customers.csv', sep='|')


customer_df.head()


customer_df['acct_num'].nunique()

1000


customer_df.shape

(1000, 15)


customer_df.columns

Index(['ssn', 'cc_num', 'first', 'last', 'gender', 'street', 'city', 'state',
       'zip', 'lat', 'long', 'city_pop', 'job', 'dob', 'acct_num'],
      dtype='object')


import os

directory = './final'
dfs = []

for filename in os.listdir(directory):
    if filename.startswith('transactions'):
        print(f'Reading {filename}...')
        filepath = os.path.join(directory, filename)
        df = pd.read_csv(filepath, sep='|')
        dfs.append(df)
    else:
        print(f'{filename} is not a CSV file. Skipping...')

if len(dfs) > 0:
    transaction_df = pd.concat(dfs, ignore_index=True)
    print(f'Successfully merged {len(dfs)} dataframes into one.')
else:
    print('No CSV files found in directory.')

Reading transactions_12.csv...
Reading transactions_126.csv...
Reading transactions_127.csv...
Reading transactions_13.csv...
customers.csv is not a CSV file. Skipping...
Reading transactions_39.csv...
Reading transactions_11.csv...
Reading transactions_119.csv...
Reading transactions_131.csv...
Reading transactions_125.csv...
Reading transactions_124.csv...
Reading transactions_130.csv...
Reading transactions_118.csv...
Reading transactions_10.csv...
Reading transactions_38.csv...
Reading transactions_14.csv...
Reading transactions_28.csv...
Reading transactions_120.csv...
Reading transactions_108.csv...
Reading transactions_109.csv...
Reading transactions_121.csv...
Reading transactions_29.csv...
Reading transactions_15.csv...
Reading transactions_17.csv...
Reading transactions_123.csv...
Reading transactions_122.csv...
Reading transactions_16.csv...
Reading transactions_59.csv...
Reading transactions_65.csv...
Reading transactions_71.csv...
Reading transactions_7.csv...
Reading transactions_6.csv...
Reading transactions_70.csv...
Reading transactions_64.csv...
Reading transactions_58.csv...
Reading transactions_72.csv...
Reading transactions_4.csv...
Reading transactions_66.csv...
Reading transactions_99.csv...
Reading transactions_98.csv...
Reading transactions_67.csv...
Reading transactions_5.csv...
Reading transactions_73.csv...
Reading transactions_77.csv...
Reading transactions_1.csv...
Reading transactions_63.csv...
Reading transactions_88.csv...
Reading transactions_89.csv...
Reading transactions_62.csv...
Reading transactions_0.csv...
Reading transactions_76.csv...
Reading transactions_60.csv...
Reading transactions_74.csv...
Reading transactions_2.csv...
Reading transactions_48.csv...
Reading transactions_49.csv...
Reading transactions_3.csv...
Reading transactions_75.csv...
Reading transactions_61.csv...
Reading transactions_78.csv...
Reading transactions_44.csv...
Reading transactions_50.csv...
Reading transactions_87.csv...
Reading transactions_93.csv...
Reading transactions_92.csv...
Reading transactions_86.csv...
Reading transactions_51.csv...
Reading transactions_45.csv...
Reading transactions_79.csv...
Reading transactions_53.csv...
Reading transactions_47.csv...
Reading transactions_90.csv...
Reading transactions_84.csv...
Reading transactions_85.csv...
Reading transactions_91.csv...
Reading transactions_46.csv...
Reading transactions_52.csv...
Reading transactions_56.csv...
Reading transactions_42.csv...
Reading transactions_8.csv...
Reading transactions_95.csv...
Reading transactions_81.csv...
Reading transactions_80.csv...
Reading transactions_94.csv...
Reading transactions_9.csv...
Reading transactions_43.csv...
Reading transactions_57.csv...
Reading transactions_41.csv...
Reading transactions_55.csv...
Reading transactions_69.csv...
Reading transactions_82.csv...
Reading transactions_96.csv...
Reading transactions_97.csv...
Reading transactions_83.csv...
Reading transactions_68.csv...
Reading transactions_54.csv...
Reading transactions_40.csv...
Reading transactions_27.csv...
Reading transactions_33.csv...
Reading transactions_107.csv...
Reading transactions_113.csv...
Reading transactions_112.csv...
Reading transactions_106.csv...
Reading transactions_32.csv...
Reading transactions_26.csv...
Reading transactions_18.csv...
Reading transactions_30.csv...
Reading transactions_24.csv...
Reading transactions_110.csv...
Reading transactions_104.csv...
Reading transactions_105.csv...
Reading transactions_111.csv...
Reading transactions_25.csv...
Reading transactions_31.csv...
Reading transactions_19.csv...
Reading transactions_35.csv...
Reading transactions_21.csv...
Reading transactions_115.csv...
Reading transactions_101.csv...
Reading transactions_129.csv...
Reading transactions_128.csv...
Reading transactions_100.csv...
Reading transactions_114.csv...
Reading transactions_20.csv...
Reading transactions_34.csv...
Reading transactions_22.csv...
Reading transactions_36.csv...
Reading transactions_102.csv...
Reading transactions_116.csv...
Reading transactions_117.csv...
Reading transactions_103.csv...
Reading transactions_37.csv...
Reading transactions_23.csv...
Successfully merged 132 dataframes into one.


transaction_df.head()


transaction_df.shape

(4260904, 10)


transaction_df.columns

Index(['cc_num', 'acct_num', 'trans_num', 'unix_time', 'category', 'amt',
       'is_fraud', 'merchant', 'merch_lat', 'merch_long'],
      dtype='object')


transaction_df['acct_num'].nunique()

983


df = customer_df.merge(transaction_df, on=['cc_num', 'acct_num'])


df.head()


df['acct_num'].nunique()

983


df.shape

(4260904, 23)


df.columns

Index(['ssn', 'cc_num', 'first', 'last', 'gender', 'street', 'city', 'state',
       'zip', 'lat', 'long', 'city_pop', 'job', 'dob', 'acct_num', 'trans_num',
       'unix_time', 'category', 'amt', 'is_fraud', 'merchant', 'merch_lat',
       'merch_long'],
      dtype='object')


df.isna().sum()

ssn           0
cc_num        0
first         0
last          0
gender        0
street        0
city          0
state         0
zip           0
lat           0
long          0
city_pop      0
job           0
dob           0
acct_num      0
trans_num     0
unix_time     0
category      0
amt           0
is_fraud      0
merchant      0
merch_lat     0
merch_long    0
dtype: int64


df.duplicated().sum()

0


df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 4260904 entries, 0 to 4260903
Data columns (total 23 columns):
 #   Column      Dtype  
---  ------      -----  
 0   ssn         object 
 1   cc_num      object 
 2   first       object 
 3   last        object 
 4   gender      object 
 5   street      object 
 6   city        object 
 7   state       object 
 8   zip         int64  
 9   lat         float64
 10  long        float64
 11  city_pop    int64  
 12  job         object 
 13  dob         object 
 14  acct_num    object 
 15  trans_num   object 
 16  unix_time   object 
 17  category    object 
 18  amt         float64
 19  is_fraud    object 
 20  merchant    object 
 21  merch_lat   float64
 22  merch_long  float64
dtypes: float64(5), int64(2), object(16)
memory usage: 780.2+ MB


df['unix_time'].nunique()

4114752


df_cleaned = df.copy()


df_cleaned['dob'] = pd.to_datetime(df_cleaned['dob'])


df_cleaned['trans_date_time'] = pd.to_datetime(df_cleaned['unix_time'], unit='s')


df_cleaned['trans_month_year'] = pd.to_datetime(df_cleaned['trans_date_time']).dt.to_period('M')
df_cleaned['quarter'] = pd.to_datetime(df_cleaned['trans_date_time']).dt.to_period('Q')


df_cleaned['first_trans_month_year'] = df_cleaned.groupby('acct_num')['trans_month_year'].transform('min')
df_cleaned['first_trans_month_year'] = df_cleaned['first_trans_month_year'].dt.to_timestamp()
age = ((df_cleaned['first_trans_month_year'] - df_cleaned['dob']).dt.days / 365.25).apply(round)
df_cleaned['age'] = age


df_cleaned.head()


import seaborn as sns
import matplotlib.pyplot as plt
palette='ch:.25'


pred_trans_df = df_cleaned.copy()


pred_trans_df['category'].nunique()

14


pred_trans_df['zip'].nunique()

939


pred_trans_df['city'].nunique()

726


pred_trans_df['state'].nunique()

51


pred_trans_df['job'].nunique()

505


pred_trans_df = pred_trans_df[pred_trans_df['is_fraud'] == 0]


pred_trans_df.shape

(4255870, 28)


pred_trans_df.columns

Index(['ssn', 'cc_num', 'first', 'last', 'gender', 'street', 'city', 'state',
       'zip', 'lat', 'long', 'city_pop', 'job', 'dob', 'acct_num', 'trans_num',
       'unix_time', 'category', 'amt', 'is_fraud', 'merchant', 'merch_lat',
       'merch_long', 'trans_date_time', 'trans_month_year', 'quarter',
       'first_trans_month_year', 'age'],
      dtype='object')


pred_trans_df.head()


pred_trans_df['month'] = pred_trans_df['trans_month_year'].dt.month
pred_trans_df['year'] = pred_trans_df['trans_month_year'].dt.year


monthly_spending = pred_trans_df.groupby(['year', 'month']).agg({'amt': ['sum', 'mean', 'max', 'min'],
                                                                 'trans_num': 'count'}).reset_index()
monthly_spending.columns = ['year', 'month', 'total_amt', 'mean_amt', 'max_amt', 'min_amt', 'trans_count']


monthly_spending.tail()


sns.lineplot(data=monthly_spending, x='month', y='total_amt', hue='year', palette=palette)
plt.ylabel('Total Monthly Spending ($)')
plt.ticklabel_format(style='plain', axis='y')
plt.yticks(np.arange(0, 1.8e7, 0.2e7))
plt.title('Total Monthly Spending Across Customers')

plt.show()


monthly_spending['year_month'] = monthly_spending['year'].astype(str) + '-' + monthly_spending['month'].astype(str)


fig, ax = plt.subplots(figsize=(18, 6))

ax.plot(monthly_spending['year_month'], monthly_spending['total_amt'], color='black')
ax.set_xlabel('Year-Month')

ax.set_xlabel('Year-Month', fontsize=12)
ax.tick_params(axis='x', rotation=45)
ax.set_ylabel('Total Spending ($)', fontsize=12)
ax.yaxis.set_major_formatter('${:.0f}'.format)

ax.set_title('Total Monthly Spending', fontsize=14)

Text(0.5, 1.0, 'Total Monthly Spending')


fig, ax = plt.subplots(figsize=(18, 6))
ax2 = ax.twinx()

ax.plot(monthly_spending['year_month'], monthly_spending['total_amt'], color='black')
ax.set_xlabel('Year-Month', fontsize=12)
ax.tick_params(axis='x', rotation=45)
ax.set_ylabel('Total Spending ($)', fontsize=12)
ax.yaxis.set_major_formatter('${:.0f}'.format)
ax.set_title('Total Monthly Spending and Transactions', fontsize=14)

ax2.bar(monthly_spending['year_month'], monthly_spending['trans_count'], color='grey', alpha=0.5)
ax2.set_ylabel('Transaction Count', fontsize=12)

plt.show()


fig, ax = plt.subplots(figsize=(18, 6))

ax.plot(monthly_spending['year_month'], monthly_spending['total_amt'], color='black')

ax.axvspan('2019-11', '2020-1', color='red', alpha=0.1)
ax.axvspan('2020-11', '2021-1', color='red', alpha=0.1)
ax.axvspan('2021-11', '2022-1', color='red', alpha=0.1)
ax.axvspan('2022-11', '2022-12', color='red', alpha=0.1)

ax.set_xlabel('Year-Month', fontsize=12)
ax.tick_params(axis='x', rotation=45)
ax.set_ylabel('Total Spending ($)', fontsize=12)
ax.yaxis.set_major_formatter('${:.0f}'.format)

ax.set_title('Total Monthly Spending', fontsize=14)

plt.show()


fig, ax = plt.subplots(figsize=(18, 6))

ax.plot(monthly_spending['year_month'], monthly_spending['total_amt'], color='black')

ax2 = ax.twinx()
ax2.bar(monthly_spending['year_month'], monthly_spending['trans_count'], color='grey', alpha=0.5)
ax2.set_ylabel('Total Transactions', fontsize=12)
ax2.yaxis.set_major_formatter('{:.0f}'.format)

ax.axvspan('2019-11', '2020-1', color='red', alpha=0.1)
ax.axvspan('2020-11', '2021-1', color='red', alpha=0.1)
ax.axvspan('2021-11', '2022-1', color='red', alpha=0.1)
ax.axvspan('2022-11', '2022-12', color='red', alpha=0.1)

ax.set_xlabel('Year-Month', fontsize=12)
ax.tick_params(axis='x', rotation=45)
ax.set_ylabel('Total Spending ($)', fontsize=12)
ax.yaxis.set_major_formatter('${:.0f}'.format)

ax.legend(['Total Spending'], loc='upper left')
ax2.legend(['Total Transactions'], loc='upper right')
plt.title('Total Monthly Spending and Transactions', fontsize=14)

plt.show()


total_spent_per_month = pred_trans_df.groupby(['acct_num', 'trans_month_year']).agg({
    'category': lambda x: x.value_counts().idxmax(),
    'age': 'min',
    'gender': 'first',
    'job': 'first',
    'city': 'first',
    'state': 'first',
    'zip': 'first',
    'trans_num': 'count',
    'amt': ['mean', 'max', 'min', 'sum']
}).reset_index()


total_spent_per_month.columns = ['acct_num', 'trans_month_year', 'category', 'age', 'gender', 'job', 'city', 'state', 'zip', 'trans_count', 'mean_amt', 'max_amt', 'min_amt', 'total_amt']


total_spent_per_month.head()


fig, axes = plt.subplots(6, 1, figsize=(16, 18))

for i, c in enumerate(['total_amt', 'mean_amt', 'trans_count', 'age', 'gender', 'state']):
    sns.histplot(data=total_spent_per_month[c], ax=axes[i], kde=True, color='orange')

plt.tight_layout()
plt.show()


customer_summary = pd.pivot_table(total_spent_per_month, 
                                  index=['acct_num'], 
                                  columns=['trans_month_year'], 
                                  values=['trans_count', 'total_amt'],
                                  fill_value=0)


customer_summary_flat = pd.DataFrame(customer_summary.to_records())

customer_summary_flat.columns = [col.replace("('", "").replace("', '", "_").replace("'))", "") 
                                 for col in customer_summary_flat.columns]


customer_summary_flat.head()


customer_summary_flat = customer_summary_flat.rename(columns={"total_amt', Period2022-12_M": "Target"})


fig, axes = plt.subplots(8, 6, figsize=(25, 25))
axes = [ax for axes_row in axes for ax in axes_row]

for i, c in enumerate(customer_summary_flat.loc[:, "total_amt', Period2018-12_M":"total_amt', Period2022-11_M"]):
    sns.scatterplot(y="Target", x=c, data=customer_summary_flat, ax=axes[i], color='orange')
    sns.regplot(y="Target", x=c, data=customer_summary_flat, ax=axes[i], scatter=False, color='red')
    corr = customer_summary_flat['Target'].corr(customer_summary_flat[c])
    axes[i].set_title('Corr: {:.2f}'.format(corr), fontsize=12)

plt.tight_layout()
plt.show()


fig, axes = plt.subplots(8, 6, figsize=(25, 25))
axes = [ax for axes_row in axes for ax in axes_row]

for i, c in enumerate(customer_summary_flat.loc[:, "total_amt', Period2018-12_M":"total_amt', Period2022-11_M"]):
    sns.boxplot(x=c, data=customer_summary_flat, ax=axes[i], color='orange', flierprops=dict(markerfacecolor='red'))
    
plt.tight_layout()
plt.show()


fig, axes = plt.subplots(7, 7, figsize=(25, 25))
axes = [ax for axes_row in axes for ax in axes_row]

for i, c in enumerate(customer_summary_flat.loc[:, "trans_count', Period2018-12_M":"trans_count', Period2022-12_M"]):
    sns.scatterplot(y="Target", x=c, data=customer_summary_flat, ax=axes[i], color='orange')
    sns.regplot(y="Target", x=c, data=customer_summary_flat, ax=axes[i], scatter=False, color='red')
    corr = customer_summary_flat['Target'].corr(customer_summary_flat[c])
    axes[i].set_title('Corr: {:.2f}'.format(corr), fontsize=12)

plt.tight_layout()
plt.show()


fig, axes = plt.subplots(7, 7, figsize=(25, 25))
axes = [ax for axes_row in axes for ax in axes_row]

for i, c in enumerate(customer_summary_flat.loc[:, "trans_count', Period2018-12_M":"trans_count', Period2022-12_M"]):
    sns.boxplot(x=c, data=customer_summary_flat, ax=axes[i], color='orange', flierprops=dict(markerfacecolor='red'))

plt.tight_layout()
plt.show()


customer_demographics = pred_trans_df[['acct_num', 'gender', 'age', 'job', 'city']]


trans_df = pd.merge(customer_summary_flat, customer_demographics, on='acct_num')


trans_df.drop_duplicates(inplace=True)


trans_df.reset_index(drop=True, inplace=True)


bins = [0, 18, 24, 34, 44, 54, 64, 200]
labels = ['<18', '18-24', '25-34', '35-44', '45-54', '55-64', '65+']


trans_df['age_group'] = pd.cut(trans_df['age'], bins=bins, labels=labels)


target_index = trans_df.columns.get_loc("Target")

cols = list(trans_df.columns)
cols.append(cols.pop(target_index))
trans_df = trans_df[cols]


trans_df.head()


sns.boxplot(x='age_group', y='Target', data=trans_df, palette='Set3')
plt.title('Dec 2022 Spending by Age Group')
plt.xticks(rotation=45)
plt.show()


sns.boxplot(x='gender', y='Target', data=trans_df, palette='Set3')
plt.title('Dec 2022 Spending by gender')
plt.xticks(rotation=45)
plt.show()


dec2022 = total_spent_per_month[total_spent_per_month['trans_month_year'] == '2022-12']


dec2022.head()


sns.boxplot(x='category', y='total_amt', data=dec2022, palette='Set3')
plt.title('Dec 2022 Spending by Category')
plt.xticks(rotation=45)
plt.show()


dec_2022 = pred_trans_df[pred_trans_df['trans_month_year'] == '2022-12']


pred_trans_df.head()


trans_df.shape

(972, 104)


correlation = trans_df.corr()

plt.figure(figsize=(50, 50))
sns.heatmap(correlation, annot=True, cmap='YlGnBu')

plt.show()

/var/folders/lk/qbgh0syd1l7_7h6ghvq233nr0000gn/T/ipykernel_92512/3535905867.py:1: FutureWarning: The default value of numeric_only in DataFrame.corr is deprecated. In a future version, it will default to False. Select only valid columns or specify the value of numeric_only to silence this warning.
  correlation = trans_df.corr()


correlation


from sklearn.model_selection import train_test_split

data_df, test_df = train_test_split(trans_df, test_size=0.25, random_state=42)

train_df, val_df = train_test_split(data_df, test_size=0.25, random_state=42)


from sklearn.preprocessing import OneHotEncoder


train_gender = train_df['gender'].values.reshape(-1, 1)
val_gender = val_df['gender'].values.reshape(-1, 1)
test_gender = test_df['gender'].values.reshape(-1, 1)


encoder = OneHotEncoder(sparse=False, handle_unknown='ignore')
encoder.fit(train_gender)

/opt/homebrew/lib/python3.10/site-packages/sklearn/preprocessing/_encoders.py:868: FutureWarning: `sparse` was renamed to `sparse_output` in version 1.2 and will be removed in 1.4. `sparse_output` is ignored unless you leave `sparse` to its default value.
  warnings.warn(

OneHotEncoder(handle_unknown='ignore', sparse=False, sparse_output=False)

OneHotEncoder(handle_unknown='ignore', sparse=False, sparse_output=False)


train_gender_encoded = encoder.transform(train_gender)
val_gender_encoded = encoder.transform(val_gender)
test_gender_encoded = encoder.transform(test_gender)


train_encoded = pd.DataFrame(train_gender_encoded, columns=encoder.get_feature_names_out(['gender']), index=train_df.index)
val_encoded = pd.DataFrame(val_gender_encoded, columns=encoder.get_feature_names_out(['gender']), index=val_df.index)
test_encoded = pd.DataFrame(test_gender_encoded, columns=encoder.get_feature_names_out(['gender']), index=test_df.index)


train_df = pd.concat([train_df.drop('gender', axis=1), train_encoded], axis=1)
val_df = pd.concat([val_df.drop('gender', axis=1), val_encoded], axis=1)
test_df = pd.concat([test_df.drop('gender', axis=1), test_encoded], axis=1)


train_df.head()


frequency_map = {}


job_frequency = train_df['job'].value_counts(normalize=True)

train_df['job_frequency'] = train_df['job'].map(job_frequency)
val_df['job_frequency'] = val_df['job'].map(job_frequency)
test_df['job_frequency'] = test_df['job'].map(job_frequency)


val_df['job_frequency'].fillna(val_df['job_frequency'].mean(), inplace=True)
test_df['job_frequency'].fillna(val_df['job_frequency'].mean(), inplace=True)


city_frequency = train_df['city'].value_counts(normalize=True)

train_df['city_frequency'] = train_df['city'].map(city_frequency)
val_df['city_frequency'] = val_df['city'].map(city_frequency)
test_df['city_frequency'] = test_df['city'].map(city_frequency)


val_df['city_frequency'].fillna(val_df['city_frequency'].mean(), inplace=True)
test_df['city_frequency'].fillna(val_df['city_frequency'].mean(), inplace=True)


age_group_mapping = {
    '<18': 1,
    '18-24': 2,
    '25-34': 3,
    '35-44': 4,
    '45-54': 5,
    '55-64': 6,
    '65+': 7
}


train_df['age_group_encoded'] = train_df['age_group'].map(age_group_mapping)
val_df['age_group_encoded'] = val_df['age_group'].map(age_group_mapping)
test_df['age_group_encoded'] = test_df['age_group'].map(age_group_mapping)


train_df.drop(['age', 'age_group','job', 'city'], axis=1, inplace=True)
val_df.drop(['age', 'age_group', 'job', 'city'], axis=1, inplace=True)
test_df.drop(['age', 'age_group', 'job', 'city'], axis=1, inplace=True)


train_df.head()


train_df.isna().sum()

acct_num                         0
total_amt', Period2018-12_M      0
total_amt', Period2019-01_M      0
total_amt', Period2019-02_M      0
total_amt', Period2019-03_M      0
total_amt', Period2019-04_M      0
total_amt', Period2019-05_M      0
total_amt', Period2019-06_M      0
total_amt', Period2019-07_M      0
total_amt', Period2019-08_M      0
total_amt', Period2019-09_M      0
total_amt', Period2019-10_M      0
total_amt', Period2019-11_M      0
total_amt', Period2019-12_M      0
total_amt', Period2020-01_M      0
total_amt', Period2020-02_M      0
total_amt', Period2020-03_M      0
total_amt', Period2020-04_M      0
total_amt', Period2020-05_M      0
total_amt', Period2020-06_M      0
total_amt', Period2020-07_M      0
total_amt', Period2020-08_M      0
total_amt', Period2020-09_M      0
total_amt', Period2020-10_M      0
total_amt', Period2020-11_M      0
total_amt', Period2020-12_M      0
total_amt', Period2021-01_M      0
total_amt', Period2021-02_M      0
total_amt', Period2021-03_M      0
total_amt', Period2021-04_M      0
total_amt', Period2021-05_M      0
total_amt', Period2021-06_M      0
total_amt', Period2021-07_M      0
total_amt', Period2021-08_M      0
total_amt', Period2021-09_M      0
total_amt', Period2021-10_M      0
total_amt', Period2021-11_M      0
total_amt', Period2021-12_M      0
total_amt', Period2022-01_M      0
total_amt', Period2022-02_M      0
total_amt', Period2022-03_M      0
total_amt', Period2022-04_M      0
total_amt', Period2022-05_M      0
total_amt', Period2022-06_M      0
total_amt', Period2022-07_M      0
total_amt', Period2022-08_M      0
total_amt', Period2022-09_M      0
total_amt', Period2022-10_M      0
total_amt', Period2022-11_M      0
trans_count', Period2018-12_M    0
trans_count', Period2019-01_M    0
trans_count', Period2019-02_M    0
trans_count', Period2019-03_M    0
trans_count', Period2019-04_M    0
trans_count', Period2019-05_M    0
trans_count', Period2019-06_M    0
trans_count', Period2019-07_M    0
trans_count', Period2019-08_M    0
trans_count', Period2019-09_M    0
trans_count', Period2019-10_M    0
trans_count', Period2019-11_M    0
trans_count', Period2019-12_M    0
trans_count', Period2020-01_M    0
trans_count', Period2020-02_M    0
trans_count', Period2020-03_M    0
trans_count', Period2020-04_M    0
trans_count', Period2020-05_M    0
trans_count', Period2020-06_M    0
trans_count', Period2020-07_M    0
trans_count', Period2020-08_M    0
trans_count', Period2020-09_M    0
trans_count', Period2020-10_M    0
trans_count', Period2020-11_M    0
trans_count', Period2020-12_M    0
trans_count', Period2021-01_M    0
trans_count', Period2021-02_M    0
trans_count', Period2021-03_M    0
trans_count', Period2021-04_M    0
trans_count', Period2021-05_M    0
trans_count', Period2021-06_M    0
trans_count', Period2021-07_M    0
trans_count', Period2021-08_M    0
trans_count', Period2021-09_M    0
trans_count', Period2021-10_M    0
trans_count', Period2021-11_M    0
trans_count', Period2021-12_M    0
trans_count', Period2022-01_M    0
trans_count', Period2022-02_M    0
trans_count', Period2022-03_M    0
trans_count', Period2022-04_M    0
trans_count', Period2022-05_M    0
trans_count', Period2022-06_M    0
trans_count', Period2022-07_M    0
trans_count', Period2022-08_M    0
trans_count', Period2022-09_M    0
trans_count', Period2022-10_M    0
trans_count', Period2022-11_M    0
trans_count', Period2022-12_M    0
Target                           0
gender_F                         0
gender_M                         0
job_frequency                    0
city_frequency                   0
age_group_encoded                0
dtype: int64


val_df.isna().sum()

acct_num                         0
total_amt', Period2018-12_M      0
total_amt', Period2019-01_M      0
total_amt', Period2019-02_M      0
total_amt', Period2019-03_M      0
total_amt', Period2019-04_M      0
total_amt', Period2019-05_M      0
total_amt', Period2019-06_M      0
total_amt', Period2019-07_M      0
total_amt', Period2019-08_M      0
total_amt', Period2019-09_M      0
total_amt', Period2019-10_M      0
total_amt', Period2019-11_M      0
total_amt', Period2019-12_M      0
total_amt', Period2020-01_M      0
total_amt', Period2020-02_M      0
total_amt', Period2020-03_M      0
total_amt', Period2020-04_M      0
total_amt', Period2020-05_M      0
total_amt', Period2020-06_M      0
total_amt', Period2020-07_M      0
total_amt', Period2020-08_M      0
total_amt', Period2020-09_M      0
total_amt', Period2020-10_M      0
total_amt', Period2020-11_M      0
total_amt', Period2020-12_M      0
total_amt', Period2021-01_M      0
total_amt', Period2021-02_M      0
total_amt', Period2021-03_M      0
total_amt', Period2021-04_M      0
total_amt', Period2021-05_M      0
total_amt', Period2021-06_M      0
total_amt', Period2021-07_M      0
total_amt', Period2021-08_M      0
total_amt', Period2021-09_M      0
total_amt', Period2021-10_M      0
total_amt', Period2021-11_M      0
total_amt', Period2021-12_M      0
total_amt', Period2022-01_M      0
total_amt', Period2022-02_M      0
total_amt', Period2022-03_M      0
total_amt', Period2022-04_M      0
total_amt', Period2022-05_M      0
total_amt', Period2022-06_M      0
total_amt', Period2022-07_M      0
total_amt', Period2022-08_M      0
total_amt', Period2022-09_M      0
total_amt', Period2022-10_M      0
total_amt', Period2022-11_M      0
trans_count', Period2018-12_M    0
trans_count', Period2019-01_M    0
trans_count', Period2019-02_M    0
trans_count', Period2019-03_M    0
trans_count', Period2019-04_M    0
trans_count', Period2019-05_M    0
trans_count', Period2019-06_M    0
trans_count', Period2019-07_M    0
trans_count', Period2019-08_M    0
trans_count', Period2019-09_M    0
trans_count', Period2019-10_M    0
trans_count', Period2019-11_M    0
trans_count', Period2019-12_M    0
trans_count', Period2020-01_M    0
trans_count', Period2020-02_M    0
trans_count', Period2020-03_M    0
trans_count', Period2020-04_M    0
trans_count', Period2020-05_M    0
trans_count', Period2020-06_M    0
trans_count', Period2020-07_M    0
trans_count', Period2020-08_M    0
trans_count', Period2020-09_M    0
trans_count', Period2020-10_M    0
trans_count', Period2020-11_M    0
trans_count', Period2020-12_M    0
trans_count', Period2021-01_M    0
trans_count', Period2021-02_M    0
trans_count', Period2021-03_M    0
trans_count', Period2021-04_M    0
trans_count', Period2021-05_M    0
trans_count', Period2021-06_M    0
trans_count', Period2021-07_M    0
trans_count', Period2021-08_M    0
trans_count', Period2021-09_M    0
trans_count', Period2021-10_M    0
trans_count', Period2021-11_M    0
trans_count', Period2021-12_M    0
trans_count', Period2022-01_M    0
trans_count', Period2022-02_M    0
trans_count', Period2022-03_M    0
trans_count', Period2022-04_M    0
trans_count', Period2022-05_M    0
trans_count', Period2022-06_M    0
trans_count', Period2022-07_M    0
trans_count', Period2022-08_M    0
trans_count', Period2022-09_M    0
trans_count', Period2022-10_M    0
trans_count', Period2022-11_M    0
trans_count', Period2022-12_M    0
Target                           0
gender_F                         0
gender_M                         0
job_frequency                    0
city_frequency                   0
age_group_encoded                0
dtype: int64


test_df.isna().sum()

acct_num                         0
total_amt', Period2018-12_M      0
total_amt', Period2019-01_M      0
total_amt', Period2019-02_M      0
total_amt', Period2019-03_M      0
total_amt', Period2019-04_M      0
total_amt', Period2019-05_M      0
total_amt', Period2019-06_M      0
total_amt', Period2019-07_M      0
total_amt', Period2019-08_M      0
total_amt', Period2019-09_M      0
total_amt', Period2019-10_M      0
total_amt', Period2019-11_M      0
total_amt', Period2019-12_M      0
total_amt', Period2020-01_M      0
total_amt', Period2020-02_M      0
total_amt', Period2020-03_M      0
total_amt', Period2020-04_M      0
total_amt', Period2020-05_M      0
total_amt', Period2020-06_M      0
total_amt', Period2020-07_M      0
total_amt', Period2020-08_M      0
total_amt', Period2020-09_M      0
total_amt', Period2020-10_M      0
total_amt', Period2020-11_M      0
total_amt', Period2020-12_M      0
total_amt', Period2021-01_M      0
total_amt', Period2021-02_M      0
total_amt', Period2021-03_M      0
total_amt', Period2021-04_M      0
total_amt', Period2021-05_M      0
total_amt', Period2021-06_M      0
total_amt', Period2021-07_M      0
total_amt', Period2021-08_M      0
total_amt', Period2021-09_M      0
total_amt', Period2021-10_M      0
total_amt', Period2021-11_M      0
total_amt', Period2021-12_M      0
total_amt', Period2022-01_M      0
total_amt', Period2022-02_M      0
total_amt', Period2022-03_M      0
total_amt', Period2022-04_M      0
total_amt', Period2022-05_M      0
total_amt', Period2022-06_M      0
total_amt', Period2022-07_M      0
total_amt', Period2022-08_M      0
total_amt', Period2022-09_M      0
total_amt', Period2022-10_M      0
total_amt', Period2022-11_M      0
trans_count', Period2018-12_M    0
trans_count', Period2019-01_M    0
trans_count', Period2019-02_M    0
trans_count', Period2019-03_M    0
trans_count', Period2019-04_M    0
trans_count', Period2019-05_M    0
trans_count', Period2019-06_M    0
trans_count', Period2019-07_M    0
trans_count', Period2019-08_M    0
trans_count', Period2019-09_M    0
trans_count', Period2019-10_M    0
trans_count', Period2019-11_M    0
trans_count', Period2019-12_M    0
trans_count', Period2020-01_M    0
trans_count', Period2020-02_M    0
trans_count', Period2020-03_M    0
trans_count', Period2020-04_M    0
trans_count', Period2020-05_M    0
trans_count', Period2020-06_M    0
trans_count', Period2020-07_M    0
trans_count', Period2020-08_M    0
trans_count', Period2020-09_M    0
trans_count', Period2020-10_M    0
trans_count', Period2020-11_M    0
trans_count', Period2020-12_M    0
trans_count', Period2021-01_M    0
trans_count', Period2021-02_M    0
trans_count', Period2021-03_M    0
trans_count', Period2021-04_M    0
trans_count', Period2021-05_M    0
trans_count', Period2021-06_M    0
trans_count', Period2021-07_M    0
trans_count', Period2021-08_M    0
trans_count', Period2021-09_M    0
trans_count', Period2021-10_M    0
trans_count', Period2021-11_M    0
trans_count', Period2021-12_M    0
trans_count', Period2022-01_M    0
trans_count', Period2022-02_M    0
trans_count', Period2022-03_M    0
trans_count', Period2022-04_M    0
trans_count', Period2022-05_M    0
trans_count', Period2022-06_M    0
trans_count', Period2022-07_M    0
trans_count', Period2022-08_M    0
trans_count', Period2022-09_M    0
trans_count', Period2022-10_M    0
trans_count', Period2022-11_M    0
trans_count', Period2022-12_M    0
Target                           0
gender_F                         0
gender_M                         0
job_frequency                    0
city_frequency                   0
age_group_encoded                0
dtype: int64


X_train = train_df.drop(["acct_num", "Target"], axis=1)
y_train = train_df["Target"]

X_val = val_df.drop(["acct_num", "Target"], axis=1)
y_val = val_df["Target"]

X_test = test_df.drop(["acct_num", "Target"], axis=1)
y_test = test_df["Target"]


from sklearn.preprocessing import StandardScaler


scaler = StandardScaler()


X_train_scaled = scaler.fit_transform(X_train)
X_val_scaled = scaler.transform(X_val)
X_test_scaled = scaler.transform(X_test)


X_train = pd.DataFrame(X_train_scaled, columns=X_train.columns)
X_val = pd.DataFrame(X_val_scaled, columns=X_val.columns)
X_test = pd.DataFrame(X_test_scaled, columns=X_test.columns)


from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.metrics import mean_absolute_error


y_mean = y_train.mean()
y_base = np.full(y_train.shape, y_mean)

mae = mean_absolute_error(y_train, y_base)
mse = mean_squared_error(y_train, y_base)
rmse = mean_squared_error(y_train, y_base, squared=False)

baseline_train = pd.DataFrame({'mae':mae,
                               'mse':mse,
                               'rmse':rmse}, index=['Baseline_Train'])


baseline_train


y_mean = y_test.mean()
y_base = np.full(y_test.shape, y_mean)

mae = mean_absolute_error(y_base, y_test)
mse = mean_squared_error(y_base, y_test)
rmse = mean_squared_error(y_base, y_test, squared=False)

baseline_test = pd.DataFrame({'mae':mae,
                               'mse':mse,
                               'rmse':rmse}, index=['Baseline_Test'])


baseline_test


def multilinear(X_train, y_train, X_test, y_test, index_train, index_test):    
    reg = LinearRegression()
    reg.fit(X_train, y_train)
    y_preds_train = reg.predict(X_train)
    y_preds_test = reg.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    multi_train = pd.DataFrame({'mae': mae,
                           'mse': mse,
                           'rmse': rmse},
                           index=[index_train])
    
    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    multi_test = pd.DataFrame({'mae': mae,
                           'mse': mse,
                           'rmse': rmse},
                           index=[index_test])

    multi_models = pd.concat([multi_train, multi_test])
    

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16,6))

    # Plot the predicted vs actual target values for the training set
    axes[0].plot(y_train, y_preds_train, 'o', color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()


    axes[1].plot(y_test, y_preds_test, 'o', color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()
 
    return multi_models


multi = multilinear(X_train, y_train, X_val, y_val, 'MultiLinear_Train', 'MultiLinear_Val')
multi


correlation = {}

for column in trans_df.columns:
    if column not in ['acct_num', 'Target']:
        if trans_df[column].dtype in [np.int64, np.float64]:
            correlation[column] = np.abs(round(trans_df['Target'].corr(trans_df[column]), 2))


sorted_correlation = dict(sorted(correlation.items(), key=lambda x:x[1], reverse=True))


feature_var = []

for key in sorted_correlation.keys():
    if sorted_correlation[key] > 0.5:
        feature_var.append(key)


X_train_feature1 = train_df[feature_var]
X_val_feature1 = val_df[feature_var]
X_test_feature1 = test_df[feature_var]


X_train_feature1_scaled = scaler.fit_transform(X_train_feature1)
X_val_feature1_scaled = scaler.transform(X_val_feature1)
X_test_feature1_scaled = scaler.transform(X_test_feature1)


X_train_feature1 = pd.DataFrame(X_train_feature1_scaled, columns=X_train_feature1.columns)
X_val_feature1 = pd.DataFrame(X_val_feature1_scaled, columns=X_val_feature1.columns)
X_test_feature1 = pd.DataFrame(X_test_feature1_scaled, columns=X_test_feature1.columns)


multi_feature1 = multilinear(X_train_feature1, y_train, X_val_feature1, y_val, 'MultiLinear_Feature1_Train', 'MultiLinear_Feature1_Val')
multi_feature1


feature_var = []

for key in sorted_correlation.keys():
    if sorted_correlation[key] > 0.7:
        feature_var.append(key)


X_train_feature2 = train_df[feature_var]
X_val_feature2 = val_df[feature_var]
X_test_feature2 = test_df[feature_var]


X_train_feature2_scaled = scaler.fit_transform(X_train_feature2)
X_val_feature2_scaled = scaler.transform(X_val_feature2)
X_test_feature2_scaled = scaler.transform(X_test_feature2)


X_train_feature2 = pd.DataFrame(X_train_feature2_scaled, columns=X_train_feature2.columns)
X_val_feature2 = pd.DataFrame(X_val_feature2_scaled, columns=X_val_feature2.columns)
X_test_feature2 = pd.DataFrame(X_test_feature2_scaled, columns=X_test_feature2.columns)


multi_feature2 = multilinear(X_train_feature2, y_train, X_val_feature2, y_val, 'MultiLinear_Feature2_Train', 'MultiLinear_Feature2_Val')
multi_feature2


feature_var = []

for key in sorted_correlation.keys():
    if sorted_correlation[key] > 0.8:
        feature_var.append(key)


X_train_feature3 = train_df[feature_var]
X_val_feature3 = val_df[feature_var]
X_test_feature3 = test_df[feature_var]


X_train_feature3_scaled = scaler.fit_transform(X_train_feature3)
X_val_feature3_scaled = scaler.transform(X_val_feature3)
X_test_feature3_scaled = scaler.transform(X_test_feature3)


X_train_feature1 = pd.DataFrame(X_train_feature3_scaled, columns=X_train_feature3.columns)
X_val_feature1 = pd.DataFrame(X_val_feature3_scaled, columns=X_val_feature3.columns)
X_test_feature1 = pd.DataFrame(X_test_feature3_scaled, columns=X_test_feature3.columns)


multi_feature3 = multilinear(X_train_feature3, y_train, X_val_feature3, y_val, 'MultiLinear_Feature3_Train', 'MultiLinear_Feature3_Val')
multi_feature3


multi_model = pd.concat([baseline_train, baseline_test, multi, multi_feature1, multi_feature2, multi_feature3])
multi_model


from sklearn.linear_model import Lasso


def lassomodel(X_train, y_train, X_test, y_test, index_train, index_test):
    lasso_reg = Lasso()
    lasso_reg.fit(X_train, y_train)
    y_preds_train = lasso_reg.predict(X_train)
    y_preds_test = lasso_reg.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    lasso_train = pd.DataFrame({'mae': mae,
                                'mse': mse,
                                'rmse': rmse},
                               index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    lasso_test = pd.DataFrame({'mae': mae,
                               'mse': mse,
                               'rmse': rmse},
                              index=[index_test])

    lasso_models = pd.concat([lasso_train, lasso_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))

    # Plot the predicted vs actual target values for the training set
    axes[0].plot(y_train, y_preds_train, 'o',
                 color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(
        f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()

    axes[1].plot(y_test, y_preds_test, 'o',
                 color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(
        f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()

    plt.show()

    return lasso_models


lasso = lassomodel(X_train, y_train, X_val, y_val, 'Lasso_Train', 'Lasso_Val')
lasso

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 2.229e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


lasso_feature1 = lassomodel(X_train_feature1, y_train, X_val_feature1, y_val, 'Lasso_FEATURE1_Train', 'Lasso_FEATURE1_Val')
lasso_feature1

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 1.766e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


lasso_feature2 = lassomodel(X_train_feature2, y_train, X_val_feature2, y_val, 'Lasso_FEATURE2_Train', 'Lasso_FEATURE2_Val')
lasso_feature2

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 1.137e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


lasso_feature3 = lassomodel(X_train_feature3, y_train, X_val_feature3, y_val, 'Lasso_FEATURE3_Train', 'Lasso_FEATURE3_Val')
lasso_feature3

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 3.340e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


lasso_model = pd.concat([lasso, lasso_feature1, lasso_feature2, lasso_feature3])
lasso_model


from sklearn.linear_model import Ridge


def ridgemodel(X_train, y_train, X_test, y_test, index_train, index_test):
    ridge_reg = Ridge()
    ridge_reg.fit(X_train, y_train)
    y_preds_train = ridge_reg.predict(X_train)
    y_preds_test = ridge_reg.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    ridge_train = pd.DataFrame({'mae': mae,
                                'mse': mse,
                                'rmse': rmse},
                               index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    ridge_test = pd.DataFrame({'mae': mae,
                               'mse': mse,
                               'rmse': rmse},
                              index=[index_test])

    ridge_models = pd.concat([ridge_train, ridge_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))

    # Plot the predicted vs actual target values for the training set
    axes[0].plot(y_train, y_preds_train, 'o',
                 color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(
        f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()

    axes[1].plot(y_test, y_preds_test, 'o',
                 color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(
        f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()

    plt.show()

    return ridge_models


ridge = ridgemodel(X_train, y_train, X_val, y_val, 'Ridge_Train', 'Ridge_Val')
ridge


ridge_feature1 = ridgemodel(X_train_feature1, y_train, X_val_feature1, y_val, 'Ridge_FEATURE1_Train', 'Ridge_FEATURE1_Val')
ridge_feature1


ridge_feature2 = ridgemodel(X_train_feature2, y_train, X_val_feature2, y_val, 'Ridge_FEATURE2_Train', 'Ridge_FEATURE2_Val')
ridge_feature2


ridge_feature3 = ridgemodel(X_train_feature3, y_train, X_val_feature3, y_val, 'Ridge_FEATURE3_Train', 'Ridge_FEATURE3_Val')
ridge_feature3


ridge_model = pd.concat([ridge, ridge_feature1, ridge_feature2, ridge_feature3])
ridge_model


from sklearn.linear_model import ElasticNet


def elasticnet(X_train, y_train, X_test, y_test, index_train, index_test):
    elastic_reg = ElasticNet()
    elastic_reg.fit(X_train, y_train)
    y_preds_train = elastic_reg.predict(X_train)
    y_preds_test = elastic_reg.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    elastic_train = pd.DataFrame({'mae': mae,
                                  'mse': mse,
                                  'rmse': rmse},
                                 index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    elastic_test = pd.DataFrame({'mae': mae,
                                 'mse': mse,
                                 'rmse': rmse},
                                index=[index_test])

    elastic_models = pd.concat([elastic_train, elastic_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))

    axes[0].plot(y_train, y_preds_train, 'o',
                 color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(
        f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()

    axes[1].plot(y_test, y_preds_test, 'o',
                 color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(
        f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()

    return elastic_models


elastic = elasticnet(X_train, y_train, X_val, y_val, 'Elastic_Train', 'Elastic_Val')
elastic

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 1.184e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


elastic_feature1 = elasticnet(X_train_feature1, y_train, X_val_feature1, y_val, 'Elastic_FEATURE1_Train', 'Elastic_FEATURE1_Val')
elastic_feature1


elastic_feature2 = elasticnet(X_train_feature2, y_train, X_val_feature2, y_val, 'Elastic_FEATURE2_Train', 'Elastic_FEATURE2_Val')
elastic_feature2


elastic_feature3 = elasticnet(X_train_feature3, y_train, X_val_feature3, y_val, 'Elastic_FEATURE3_Train', 'Elastic_FEATURE3_Val')
elastic_feature3

/opt/homebrew/lib/python3.10/site-packages/sklearn/linear_model/_coordinate_descent.py:631: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 3.341e+09, tolerance: 6.038e+06
  model = cd_fast.enet_coordinate_descent(


elastic_model = pd.concat([elastic, elastic_feature1, elastic_feature2, elastic_feature3])
elastic_model


from sklearn.tree import DecisionTreeRegressor, plot_tree


def decision_tree_regression(X_train, y_train, X_test, y_test, index_train, index_test):
    regressor = DecisionTreeRegressor(random_state=42).fit(X_train, y_train)
    
    y_preds_train = regressor.predict(X_train)
    y_preds_test = regressor.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    dt_train = pd.DataFrame({'mae': mae,
                                  'mse': mse,
                                  'rmse': rmse},
                                 index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    dt_test = pd.DataFrame({'mae': mae,
                                 'mse': mse,
                                 'rmse': rmse},
                                index=[index_test])
    
    dt_models = pd.concat([dt_train, dt_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(24, 6))
    axes[0].set_title(f'Decision Tree: {index_train}')
    plot_tree(regressor, ax=axes[0], filled=True)

    axes[1].set_title(f'Decision  Tree: {index_test}')
    plot_tree(regressor, ax=axes[1], filled=True)
    
    plt.tight_layout()
    plt.show()

    feature_importances = regressor.feature_importances_
    sorted_indices = np.argsort(feature_importances)[::-1]
    
    feature_names = X_train.columns.values
    
    sorted_feature_importances = feature_importances[sorted_indices]
    sorted_feature_names = feature_names[sorted_indices]
    
    plt.figure(figsize=(6, 20))
    plt.barh(range(len(sorted_feature_importances)), sorted_feature_importances[::-1], align='center')
    plt.yticks(range(len(sorted_feature_importances)), sorted_feature_names[::-1])
    plt.xlabel("Feature Importance")
    plt.ylabel("Features")
    plt.title("Decision Tree Regressor - Feature Importance")
    plt.show()

    return dt_models


dt = decision_tree_regression(X_train, y_train, X_val, y_val, 'Dtregressor_Train', 'Dtregressor_Val')
dt


dt_feature1 = decision_tree_regression(X_train_feature1, y_train, X_val_feature1, y_val, 'Dtregressor_FEATURE1_Train', 'Dtregressor_FEATURE1_Val')
dt_feature1


dt_feature2 = decision_tree_regression(X_train_feature2, y_train, X_val_feature2, y_val, 'Dtregressor_FEATURE2_Train', 'Dtregressor_FEATURE2_Val')
dt_feature2


dt_feature3 = decision_tree_regression(X_train_feature3, y_train, X_val_feature3, y_val, 'Dtregressor_FEATURE3_Train', 'Dtregressor_FEATURE3_Val')
dt_feature3


max_depth = [2, 5, 10, 20, 50, 100, 150, 200, None]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_depth:
    regressor = DecisionTreeRegressor(random_state=42, max_depth=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_depth = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_depth)
result_max_depth


def plot_performance(parameter, xlabel):

    fig, (ax1, ax2, ax3) = plt.subplots(1, 3, figsize=(16, 5))

    ax1.plot(parameter, train_mae, label='Mean Absolute Errors: Train')
    ax1.plot(parameter, val_mae, label='Mean Absolute Errors: Validation')
    ax1.legend()
    ax1.set_xlabel(xlabel)
    ax1.set_ylabel('MAE')
    ax1.set_title('Mean Absolute Error')

    ax2.plot(parameter, train_mse, label='Mean Squared Errors: Train')
    ax2.plot(parameter, val_mse, label='Mean Squared Errors: Validation')
    ax2.legend()
    ax2.set_xlabel(xlabel)
    ax2.set_ylabel('MSE')
    ax2.set_title('Mean Squared Error')

    ax3.plot(parameter, train_rmse, label='Root Mean Squared Errors: Train')
    ax3.plot(parameter, val_rmse, label='Root Mean Squared Errors: Validation')
    ax3.legend()
    ax3.set_xlabel(xlabel)
    ax3.set_ylabel('RMSE')
    ax3.set_title('Root Mean Squared Errors')
    
    plt.subplots_adjust(wspace=0.4)
    plt.show()


plot_performance(max_depth, 'Number of Max Depth')


min_sample_split = [2, 5, 10, 20, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_sample_split:
    regressor = DecisionTreeRegressor(random_state=42, max_depth=5, min_samples_split=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_split = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_sample_split)
result_min_split


plot_performance(min_sample_split, 'Number of min_samples_split')


min_samples_leaf = [2, 5, 10, 20, 50, 100, 150, 200]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_samples_leaf:
    regressor = DecisionTreeRegressor(random_state=42, max_depth=5, min_samples_split=50, min_samples_leaf=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_leaf = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_samples_leaf)
result_min_leaf


plot_performance(min_samples_leaf, 'Number of min_samples_leaf')


max_features = list(range(1, 40))

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_features:
    regressor = DecisionTreeRegressor(random_state=42, max_depth=5, min_samples_split=50, min_samples_leaf=2, max_features=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_features = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_features)
result_max_features


plot_performance(max_features, 'Number of max_features')


criterion = ['absolute_error', 'squared_error', 'friedman_mse', 'poisson']

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in criterion:
    regressor = DecisionTreeRegressor(random_state=42, max_depth=5, min_samples_split=50, min_samples_leaf=5, max_features=10, criterion=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_criterion = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=criterion)
result_criterion


plot_performance(criterion, 'Criterion function')


import altair as alt

def decision_tree_regression_tuning(X_train, y_train, X_test, y_test, index_train, index_test):
    regressor = DecisionTreeRegressor(random_state=42, max_depth=5, min_samples_split=50, min_samples_leaf=5, max_features=10, criterion='squared_error').fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_test = regressor.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    dt_train = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                            index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    dt_test = pd.DataFrame({'mae': mae,
                            'mse': mse,
                            'rmse': rmse},
                           index=[index_test])

    dt_models = pd.concat([dt_train, dt_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(24, 6))
    axes[0].set_title(f'Decision Tree: {index_train}')
    plot_tree(regressor, ax=axes[0], filled=True)

    axes[1].set_title(f'Decision  Tree: {index_test}')
    plot_tree(regressor, ax=axes[1], filled=True)

    plt.tight_layout()
    plt.show()

    feature_importances = regressor.feature_importances_
    sorted_indices = np.argsort(feature_importances)[::-1]
    
    feature_names = X_train.columns.values
    
    sorted_feature_importances = feature_importances[sorted_indices]
    sorted_feature_names = feature_names[sorted_indices]
    
    plt.figure(figsize=(6, 20))
    plt.barh(range(len(sorted_feature_importances)), sorted_feature_importances[::-1], align='center')
    plt.yticks(range(len(sorted_feature_importances)), sorted_feature_names[::-1])
    plt.xlabel("Feature Importance")
    plt.ylabel("Features")
    plt.title("Decision Tree Regressor - Feature Importance")
    plt.show()

    return dt_models


dt_tuning = decision_tree_regression_tuning(X_train, y_train, X_val, y_val, 'DT_Tune_Train', 'DT_Tune_Val')
dt_tuning


dt_feature1_tuning = decision_tree_regression_tuning(X_train_feature1, y_train, X_val_feature1, y_val, 'DT_Tune_FEATURE1_Train', 'DT_Tune_FEATURE1_Val')
dt_feature1_tuning


dt_feature2_tuning = decision_tree_regression_tuning(X_train_feature2, y_train, X_val_feature2, y_val, 'DT_Tune_FEATURE2_Train', 'DT_Tune_FEATURE2_Val')
dt_feature2_tuning


dt_feature3_tuning = decision_tree_regression_tuning(X_train_feature3, y_train, X_val_feature3, y_val, 'DT_Tune_FEATURE3_Train', 'DT_Tune_FEATURE3_Val')
dt_feature3_tuning


dt_model = pd.concat([dt, dt_feature1, dt_feature2, dt_feature3, dt_tuning, dt_feature1_tuning, dt_feature2_tuning, dt_feature3_tuning])
dt_model


from sklearn.ensemble import RandomForestRegressor


def random_forest_regressor(X_train, y_train, X_test, y_test, index_train, index_test):
    regressor = RandomForestRegressor(random_state=42).fit(X_train, y_train)
    
    y_preds_train = regressor.predict(X_train)
    y_preds_test = regressor.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    rf_train = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                            index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    rf_test = pd.DataFrame({'mae': mae,
                            'mse': mse,
                            'rmse': rmse},
                           index=[index_test])
    
    dt_models = pd.concat([rf_train, rf_test])
    
    feature_importances = regressor.feature_importances_
    sorted_indices = np.argsort(feature_importances)[::-1]
    
    feature_names = X_train.columns.values
    
    sorted_feature_importances = feature_importances[sorted_indices]
    sorted_feature_names = feature_names[sorted_indices]
    
    plt.figure(figsize=(6, 20))
    plt.barh(range(len(sorted_feature_importances)), sorted_feature_importances[::-1], align='center')
    plt.yticks(range(len(sorted_feature_importances)), sorted_feature_names[::-1])
    plt.xlabel("Feature Importance")
    plt.ylabel("Features")
    plt.title("Random Forest Regressor - Feature Importance")
    plt.show()
    
    return dt_models


rf = random_forest_regressor(X_train, y_train, X_val, y_val, 'RFregressor_Train', 'RFregressor_Val')
rf


rf_feature1 = random_forest_regressor(X_train_feature1, y_train, X_val_feature1, y_val, 'RFregressor_FEATURE1_Train', 'RFregressor_FEATURE1_Val')
rf_feature1


rf_feature2 = random_forest_regressor(X_train_feature2, y_train, X_val_feature2, y_val, 'RFregressor_FEATURE2_Train', 'RFregressor_FEATURE2_Val')
rf_feature2


rf_feature3= random_forest_regressor(X_train_feature3, y_train, X_val_feature3, y_val, 'RFregressor_FEATURE3_Train', 'RFregressor_FEATURE3_Val')
rf_feature3


n_estimators = [2, 5, 10, 20, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in n_estimators:
    regressor = RandomForestRegressor(random_state=42, n_estimators=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_n_estimators = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=n_estimators)
result_n_estimators


plot_performance(n_estimators, 'Number of n_estimators')


max_depth = [2, 5, 10, 20, 50, 100, 150, 200, None]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_depth:
    regressor = RandomForestRegressor(random_state=42, n_estimators=100, max_depth=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_depth = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_depth)
result_max_depth


plot_performance(max_depth, 'Number of max_depth')


min_sample_split = [2, 5, 10, 20, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_sample_split:
    regressor = RandomForestRegressor(random_state=42, n_estimators=100, max_depth=10, min_samples_split=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_split = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_sample_split)
result_min_split


plot_performance(min_sample_split, 'Number of min_samples_split')


min_samples_leaf = [2, 5, 10, 20, 50, 100, 150, 200]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_samples_leaf:
    regressor = RandomForestRegressor(random_state=42, n_estimators=100, max_depth=10, min_samples_split=50, min_samples_leaf=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_leaf = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_samples_leaf)
result_min_leaf


plot_performance(min_samples_leaf, 'Number of min_samples_leaf')


max_features = list(range(1, 100))

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_features:
    regressor = RandomForestRegressor(random_state=42, n_estimators=100, max_depth=10, min_samples_split=50, min_samples_leaf=5, max_features=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_features = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_features)
result_max_features


result_max_features


plot_performance(max_features, 'Number of max_features')


def random_forest_regressor_tuning(X_train, y_train, X_test, y_test, index_train, index_test):
    regressor = RandomForestRegressor(random_state=42, n_estimators=100, max_depth=10, min_samples_split=50, min_samples_leaf=5, max_features=95).fit(X_train, y_train)
    
    y_preds_train = regressor.predict(X_train)
    y_preds_test = regressor.predict(X_test)

    mse = mean_squared_error(y_train, y_preds_train)
    mae = mean_absolute_error(y_train, y_preds_train)
    rmse = mean_squared_error(y_train, y_preds_train, squared=False)

    rf_train = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                            index=[index_train])

    mse = mean_squared_error(y_test, y_preds_test)
    mae = mean_absolute_error(y_test, y_preds_test)
    rmse = mean_squared_error(y_test, y_preds_test, squared=False)

    rf_test = pd.DataFrame({'mae': mae,
                            'mse': mse,
                            'rmse': rmse},
                           index=[index_test])
    
    dt_models = pd.concat([rf_train, rf_test])
    
    feature_importances = regressor.feature_importances_
    sorted_indices = np.argsort(feature_importances)[::-1]
    
    feature_names = X_train.columns.values
    
    sorted_feature_importances = feature_importances[sorted_indices]
    sorted_feature_names = feature_names[sorted_indices]
    
    plt.figure(figsize=(6, 20))
    plt.barh(range(len(sorted_feature_importances)), sorted_feature_importances[::-1], align='center')
    plt.yticks(range(len(sorted_feature_importances)), sorted_feature_names[::-1])
    plt.xlabel("Feature Importance")
    plt.ylabel("Features")
    plt.title("Random Forest Regressor - Feature Importance")
    plt.show()
    
    return dt_models


rf_tuning = random_forest_regressor_tuning(X_train, y_train, X_val, y_val, 'RF_Tune_Train', 'RF_Tune_Val')
rf_tuning


rf_feature1_tuning = random_forest_regressor_tuning(X_train_feature1, y_train, X_val_feature1, y_val, 'RF_Tune_FEATURE1_Train', 'RF_Tune_FEATURE1_Val')
rf_feature1_tuning


rf_feature2_tuning = random_forest_regressor_tuning(X_train_feature2, y_train, X_val_feature2, y_val, 'RF_Tune_FEATURE2_Train', 'RF_Tune_FEATURE2_Val')
rf_feature2_tuning


rf_feature3_tuning = random_forest_regressor_tuning(X_train_feature3, y_train, X_val_feature3, y_val, 'RF_Tune_FEATURE3_Train', 'RF_Tune_FEATURE3_Val')
rf_feature3_tuning


rf_model = pd.concat([rf, rf_feature1, rf_feature2, rf_feature3, rf_tuning, rf_feature1_tuning, rf_feature2_tuning, rf_feature3_tuning])
rf_model


from sklearn.ensemble import GradientBoostingRegressor


def xgboost(X_train, y_train, X_test, y_test, index_train, index_test):
    xgboost_reg = GradientBoostingRegressor().fit(X_train, y_train)
    
    y_preds_train = xgboost_reg.predict(X_train)
    y_preds_test = xgboost_reg.predict(X_test)

    mse = mean_squared_error(y_preds_train, y_train)
    mae = mean_absolute_error(y_preds_train, y_train)
    rmse = mean_squared_error(y_preds_train, y_train, squared=False)

    xgboost_train = pd.DataFrame({'mae': mae,
                                  'mse': mse,
                                  'rmse': rmse},
                                 index=[index_train])

    mse = mean_squared_error(y_preds_test, y_test)
    mae = mean_absolute_error(y_preds_test, y_test)
    rmse = mean_squared_error(y_preds_test, y_test, squared=False)

    xgboost_test = pd.DataFrame({'mae': mae,
                                 'mse': mse,
                                 'rmse': rmse},
                                index=[index_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))

    # Plot the predicted vs actual target values for the training set
    axes[0].plot(y_train, y_preds_train, 'o',
                 color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(
        f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()

    axes[1].plot(y_test, y_preds_test, 'o',
                 color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(
        f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()

    plt.show()

    xgboost_models = pd.concat([xgboost_train, xgboost_test])

    return xgboost_models


xg = xgboost(X_train, y_train, X_val, y_val, 'XGBoost_Train', 'XGBoost_Val')
xg


xg_feature1 = xgboost(X_train_feature1, y_train, X_val_feature1, y_val, 'XGBoost_FEATURE1_Train', 'XGBoost_FEATURE1_Val')
xg_feature1


xg_feature2 = xgboost(X_train_feature2, y_train, X_val_feature2, y_val, 'XGBoost_FEATURE2_Train', 'XGBoost_FEATURE2_Val')
xg_feature2


xg_feature3 = xgboost(X_train_feature3, y_train, X_val_feature3, y_val, 'XGBoost_FEATURE3_Train', 'XGBoost_FEATURE3_Val')
xg_feature3


learning_rate = [0.001, 0.01, 0.1, 0.15, 0.2, 0.3, 0.4, 0.5, 1]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in learning_rate:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_learning_rate = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=learning_rate)
result_learning_rate


plot_performance(learning_rate, 'Number of learning_rate')


n_estimators = [2, 5, 10, 20, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in n_estimators:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_n_estimators = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=n_estimators)
result_n_estimators


plot_performance(n_estimators, 'Number of n_estimators')


max_depth = list(range(1, 20))

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_depth:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_depth = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_depth)
result_max_depth


plot_performance(max_depth, 'Number of max_depth')


min_sample_split = [2, 5, 10, 20, 50, 100, 150, 200, 250, 300, 350, 400, 450, 500]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_sample_split:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=3, min_samples_split=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_split = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_sample_split)
result_min_split


plot_performance(min_sample_split, 'Number of min_samples_split')


min_samples_leaf = [1, 2, 5, 10, 20, 50, 100, 150, 200]

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in min_samples_leaf:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=3, min_samples_split=5, min_samples_leaf=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_min_leaf = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=min_samples_leaf)
result_min_leaf


plot_performance(min_samples_leaf, 'Number of min_samples_leaf')


max_features = list(range(1, 70))

train_mae = []
val_mae = []
train_mse = []
val_mse = []
train_rmse = []
val_rmse = []

for k in max_features:
    regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=3, min_samples_split=5, min_samples_leaf=1, max_features=k).fit(X_train, y_train)

    y_preds_train = regressor.predict(X_train)
    y_preds_val = regressor.predict(X_val)

    train_mae.append(mean_absolute_error(y_train, y_preds_train))
    val_mae.append(mean_absolute_error(y_val, y_preds_val))

    train_mse.append(mean_squared_error(y_train, y_preds_train))
    val_mse.append(mean_squared_error(y_val, y_preds_val))

    train_rmse.append(mean_squared_error(y_train, y_preds_train, squared=False))
    val_rmse.append(mean_squared_error(y_val, y_preds_val, squared=False))

result_max_features = pd.DataFrame({'train_mae': train_mae,
                                 'test_mae': val_mae,
                                 'train_mse': train_mse,
                                 'test_mse': val_mse,
                                 'train_rmse': train_rmse,
                                 'test_rmse': val_rmse}, index=max_features)
result_max_features


plot_performance(max_features, 'Number of max_features')


def xgboost_tuning(X_train, y_train, X_test, y_test, index_train, index_test):
    xgboost_reg = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=3, min_samples_split=5, min_samples_leaf=1, max_features=10).fit(X_train, y_train)
    
    y_preds_train = xgboost_reg.predict(X_train)
    y_preds_test = xgboost_reg.predict(X_test)

    mse = mean_squared_error(y_preds_train, y_train)
    mae = mean_absolute_error(y_preds_train, y_train)
    rmse = mean_squared_error(y_preds_train, y_train, squared=False)

    xgboost_train = pd.DataFrame({'mae': mae,
                                  'mse': mse,
                                  'rmse': rmse},
                                 index=[index_train])

    mse = mean_squared_error(y_preds_test, y_test)
    mae = mean_absolute_error(y_preds_test, y_test)
    rmse = mean_squared_error(y_preds_test, y_test, squared=False)

    xgboost_test = pd.DataFrame({'mae': mae,
                                 'mse': mse,
                                 'rmse': rmse},
                                index=[index_test])

    fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))

    axes[0].plot(y_train, y_preds_train, 'o',
                 color='orange', label='Predictions')
    axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

    axes[0].set_xlabel('Actual')
    axes[0].set_ylabel('Predicted')
    axes[0].set_title(
        f'{index_train}: Comparison of Actual vs. Predicted Target')

    axes[0].legend()

    axes[1].plot(y_test, y_preds_test, 'o',
                 color='orange', label='Predictions')
    axes[1].plot(y_test, y_test, '-', color='red', label='Actual')

    axes[1].set_xlabel('Actual')
    axes[1].set_ylabel('Predicted')
    axes[1].set_title(
        f'{index_test}: Comparison of Actual vs. Predicted Target')

    axes[1].legend()

    plt.show()

    xgboost_models = pd.concat([xgboost_train, xgboost_test])

    return xgboost_models


xg_tuning = xgboost_tuning(X_train, y_train, X_val, y_val, 'XGBoost_Tune_Train', 'XGBosst_Tune_Val')
xg_tuning


xg_feature1_tuning = xgboost_tuning(X_train_feature1, y_train, X_val_feature1, y_val, 'XGBoost_Tune_FEATURE1_Train', 'XGBosst_Tune_FEATURE1_Val')
xg_feature1_tuning


xg_feature2_tuning = xgboost_tuning(X_train_feature2, y_train, X_val_feature2, y_val, 'XGBoost_Tune_FEATURE2_Train', 'XGBosst_Tune_FEATURE2_Val')
xg_feature2_tuning


xg_feature3_tuning = xgboost_tuning(X_train_feature3, y_train, X_val_feature3, y_val, 'XGBoost_Tune_FEATURE3_Train', 'XGBosst_Tune_FEATURE3_Val')
xg_feature3_tuning


from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import uniform, randint


param_grid = {
    'learning_rate': uniform(0.001, 0.3),
    'n_estimators': randint(2, 100),
    'max_depth': randint(1, 5),
    'min_samples_split': [2, 5, 10, 20, 50, 100],
    'min_samples_leaf': [1, 2, 5, 10, 20, 50, 100],
    'max_features': randint(1, 10)
}


gb_regressor = GradientBoostingRegressor()


random_search = RandomizedSearchCV(
    estimator=gb_regressor,
    param_distributions=param_grid,
    n_iter=10,
    scoring='neg_mean_squared_error',
    cv=5,
    random_state=42
)


random_search.fit(X_train, y_train)

RandomizedSearchCV(cv=5, estimator=GradientBoostingRegressor(),
                   param_distributions={'learning_rate': <scipy.stats._distn_infrastructure.rv_continuous_frozen object at 0x386016980>,
                                        'max_depth': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x46ef06230>,
                                        'max_features': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x46ef074f0>,
                                        'min_samples_leaf': [1, 2, 5, 10, 20,
                                                             50, 100],
                                        'min_samples_split': [2, 5, 10, 20, 50,
                                                              100],
                                        'n_estimators': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x41bed3550>},
                   random_state=42, scoring='neg_mean_squared_error')

RandomizedSearchCV(cv=5, estimator=GradientBoostingRegressor(),
                   param_distributions={'learning_rate': <scipy.stats._distn_infrastructure.rv_continuous_frozen object at 0x386016980>,
                                        'max_depth': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x46ef06230>,
                                        'max_features': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x46ef074f0>,
                                        'min_samples_leaf': [1, 2, 5, 10, 20,
                                                             50, 100],
                                        'min_samples_split': [2, 5, 10, 20, 50,
                                                              100],
                                        'n_estimators': <scipy.stats._distn_infrastructure.rv_discrete_frozen object at 0x41bed3550>},
                   random_state=42, scoring='neg_mean_squared_error')

GradientBoostingRegressor()

GradientBoostingRegressor()


best_params = random_search.best_params_
best_estimator = random_search.best_score_


best_params

{'learning_rate': 0.12095829151457664,
 'max_depth': 4,
 'max_features': 3,
 'min_samples_leaf': 10,
 'min_samples_split': 20,
 'n_estimators': 65}


best_estimator

-15708693.11887255


xg_random = GradientBoostingRegressor(**best_params).fit(X_train, y_train)


y_preds_train = xg_random.predict(X_train)
y_preds_val = xg_random.predict(X_val)

mse = mean_squared_error(y_preds_train, y_train)
mae = mean_absolute_error(y_preds_train, y_train)
rmse = mean_squared_error(y_preds_train, y_train, squared=False)

xgboost_random_train = pd.DataFrame({'mae': mae,
                              'mse': mse,
                              'rmse': rmse},
                             index=['XGBoost_Random_Training'])

mse = mean_squared_error(y_preds_val, y_val)
mae = mean_absolute_error(y_preds_val, y_val)
rmse = mean_squared_error(y_preds_val, y_val, squared=False)

xgboost_random_val = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                            index=['XGBoost_Random_Validating'])

xgboost_random = pd.concat([xgboost_random_train, xgboost_random_val])
xgboost_random


fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(16, 6))


axes[0].plot(y_train, y_preds_train, 'o',
             color='orange', label='Predictions')
axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

axes[0].set_xlabel('Actual')
axes[0].set_ylabel('Predicted')
axes[0].set_title('XGBoost_Random_Train: Comparison of Actual vs. Predicted Target')

axes[0].legend()

axes[1].plot(y_val, y_preds_val, 'o',
             color='orange', label='Predictions')
axes[1].plot(y_val, y_val, '-', color='red', label='Actual')

axes[1].set_xlabel('Actual')
axes[1].set_ylabel('Predicted')
axes[1].set_title('XGBoost_Random_Val: Comparison of Actual vs. Predicted Target')

axes[1].legend()

<matplotlib.legend.Legend at 0x3867104c0>


xg_model = pd.concat([xg, xg_feature1, xg_feature2, xg_feature3, xg_tuning, xg_feature1_tuning, xg_feature2_tuning, xg_feature3_tuning, xgboost_random])
xg_model


multi_model


lasso_model


ridge_model


elastic_model


dt_model


rf_model


xg_model


xg_tuning


xg_regressor = GradientBoostingRegressor(random_state=42, learning_rate=0.3, n_estimators=10, max_depth=3, min_samples_split=5, min_samples_leaf=1, max_features=10).fit(X_train, y_train)


y_preds_train = xg_regressor.predict(X_train)
y_preds_val = xg_regressor.predict(X_val)
y_preds_test = xg_regressor.predict(X_test)

mse = mean_squared_error(y_preds_train, y_train)
mae = mean_absolute_error(y_preds_train, y_train)
rmse = mean_squared_error(y_preds_train, y_train, squared=False)

xgboost_train = pd.DataFrame({'mae': mae,
                              'mse': mse,
                              'rmse': rmse},
                             index=['XGBoost_Training'])

mse = mean_squared_error(y_preds_val, y_val)
mae = mean_absolute_error(y_preds_val, y_val)
rmse = mean_squared_error(y_preds_val, y_val, squared=False)

xgboost_val = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                            index=['XGBoost_Validating'])

mse = mean_squared_error(y_preds_test, y_test)
mae = mean_absolute_error(y_preds_test, y_test)
rmse = mean_squared_error(y_preds_test, y_test, squared=False)

xgboost_test = pd.DataFrame({'mae': mae,
                             'mse': mse,
                             'rmse': rmse},
                             index=['XGBoost_Testing'])

xgboost_models = pd.concat([xgboost_train, xgboost_val, xgboost_test])
xgboost_models


fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(20, 6))


axes[0].plot(y_train, y_preds_train, 'o',
             color='orange', label='Predictions')
axes[0].plot(y_train, y_train, '-', color='red', label='Actual')

axes[0].set_xlabel('Actual')
axes[0].set_ylabel('Predicted')
axes[0].set_title('XGBoost_Train: Comparison of Actual vs. Predicted Target')

axes[0].legend()

axes[1].plot(y_val, y_preds_val, 'o',
             color='orange', label='Predictions')
axes[1].plot(y_val, y_val, '-', color='red', label='Actual')

axes[1].set_xlabel('Actual')
axes[1].set_ylabel('Predicted')
axes[1].set_title('XGBoost_Val: Comparison of Actual vs. Predicted Target')

axes[1].legend()

axes[2].plot(y_test, y_preds_test, 'o',
             color='orange', label='Predictions')
axes[2].plot(y_test, y_test, '-', color='red', label='Actual')

axes[2].set_xlabel('Actual')
axes[2].set_ylabel('Predicted')
axes[2].set_title('XGBoost_Test: Comparison of Actual vs. Predicted Target')

axes[2].legend()

plt.show()

	ssn	cc_num	first	last	gender	street	city	state	zip	lat	long	city_pop	job	dob	acct_num
0	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787
1	715-55-5575	4351161559407816183	Elaine	Fuller	F	310 Kendra Common Apt. 164	Leland	NC	28451	34.2680	-78.0578	27112	Professor Emeritus	1963-06-07	917558277935
2	167-48-5821	4192832764832	Michael	Cameron	M	05641 Robin Port	Cordova	SC	29039	33.4275	-80.8857	4215	International aid/development worker	1973-05-30	718172762479
3	406-83-7518	4238849696532874	Brandon	Williams	M	26916 Carlson Mountain	Birmingham	AL	35242	33.3813	-86.7046	493806	Seismic interpreter	1942-12-26	947268892251
4	697-93-1877	4514627048281480	Lisa	Hernandez	F	809 Burns Creek	Fargo	GA	31631	30.7166	-82.5801	559	Medical laboratory scientific officer	1939-05-22	888335239225

	cc_num	acct_num	trans_num	unix_time	category	amt	merchant	merch_lat	merch_long
0	4896331812335761701	149852234418	f3ec0819590302134f03ffdc2f44697f	1646060228	gas_transport	65.17	Larson, Ryan and Huang	38.143430	-90.327335
1	4896331812335761701	149852234418	c1607c993e41f2c3b42d72d1506bef7b	1644848624	gas_transport	47.58	Myers-Reed	39.119498	-90.760379
2	4896331812335761701	149852234418	6f530db25d20fe351249a54491fd3fde	1645632153	gas_transport	64.43	Baker-Bullock	39.384368	-90.361517
3	4896331812335761701	149852234418	6d11805f2acd938fec99376001afafe8	1645311286	gas_transport	82.47	Spencer-Hall	39.443567	-89.752400
4	4896331812335761701	149852234418	605342f297c575cb1ccf2c08cad082ee	1641571926	gas_transport	50.28	King, Rodriguez and Hancock	38.857278	-89.609525

	ssn	cc_num	first	last	gender	street	city	state	zip	lat	long	city_pop	job	dob	acct_num	trans_num	unix_time	category	amt	merchant	merch_lat	merch_long
0	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	91ab12e73ef38206e1121e9648d2408d	1558719550	gas_transport	69.12	Phillips Group	39.491416	-75.588522
1	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	071553d533a6822a4431c354c434ddcb	1569425519	grocery_pos	68.11	Tucker Ltd	40.890319	-75.573359
2	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	0cfad38ef15e4749eff68dc83f62c151	1577205601	misc_net	40.35	Dixon PLC	39.244958	-74.475327
3	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	5782693d7c70f062f258cb30bfa8900f	1571428238	grocery_pos	96.22	Lambert-Cooper	39.656925	-75.802342
4	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	35fd7db657d7e30dd608c37f7798186e	1549840400	gas_transport	71.89	Griffith LLC	40.313342	-74.220434

	ssn	cc_num	first	last	gender	street	city	state	zip	lat	long	city_pop	job	dob	acct_num	trans_num	unix_time	category	amt	merchant	merch_lat	merch_long	trans_date_time	trans_month_year	quarter	first_trans_month_year	age
0	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	91ab12e73ef38206e1121e9648d2408d	1558719550	gas_transport	69.12	Phillips Group	39.491416	-75.588522	2019-05-24 17:39:10	2019-05	2019Q2	2018-12-01	59
1	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	071553d533a6822a4431c354c434ddcb	1569425519	grocery_pos	68.11	Tucker Ltd	40.890319	-75.573359	2019-09-25 15:31:59	2019-09	2019Q3	2018-12-01	59
2	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	0cfad38ef15e4749eff68dc83f62c151	1577205601	misc_net	40.35	Dixon PLC	39.244958	-74.475327	2019-12-24 16:40:01	2019-12	2019Q4	2018-12-01	59
3	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	5782693d7c70f062f258cb30bfa8900f	1571428238	grocery_pos	96.22	Lambert-Cooper	39.656925	-75.802342	2019-10-18 19:50:38	2019-10	2019Q4	2018-12-01	59
4	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	35fd7db657d7e30dd608c37f7798186e	1549840400	gas_transport	71.89	Griffith LLC	40.313342	-74.220434	2019-02-10 23:13:20	2019-02	2019Q1	2018-12-01	59

	ssn	cc_num	first	last	gender	street	city	state	zip	lat	long	city_pop	job	dob	acct_num	trans_num	unix_time	category	amt	merchant	merch_lat	merch_long	trans_date_time	trans_month_year	quarter	first_trans_month_year	age
0	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	91ab12e73ef38206e1121e9648d2408d	1558719550	gas_transport	69.12	Phillips Group	39.491416	-75.588522	2019-05-24 17:39:10	2019-05	2019Q2	2018-12-01	59
1	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	071553d533a6822a4431c354c434ddcb	1569425519	grocery_pos	68.11	Tucker Ltd	40.890319	-75.573359	2019-09-25 15:31:59	2019-09	2019Q3	2018-12-01	59
2	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	0cfad38ef15e4749eff68dc83f62c151	1577205601	misc_net	40.35	Dixon PLC	39.244958	-74.475327	2019-12-24 16:40:01	2019-12	2019Q4	2018-12-01	59
3	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	5782693d7c70f062f258cb30bfa8900f	1571428238	grocery_pos	96.22	Lambert-Cooper	39.656925	-75.802342	2019-10-18 19:50:38	2019-10	2019Q4	2018-12-01	59
4	115-04-4507	4218196001337	Jonathan	Johnson	M	863 Lawrence Valleys	Ambler	PA	19002	40.1809	-75.2156	32412	Accounting technician	1959-10-03	888022315787	35fd7db657d7e30dd608c37f7798186e	1549840400	gas_transport	71.89	Griffith LLC	40.313342	-74.220434	2019-02-10 23:13:20	2019-02	2019Q1	2018-12-01	59

	year	month	total_amt	mean_amt	max_amt	min_amt	trans_count
44	2022	8	9810985.07	63.096803	24583.86	1.0	155491
45	2022	9	7837465.56	62.719293	16460.30	1.0	124961
46	2022	10	8217907.95	62.749845	25159.92	1.0	130963
47	2022	11	8046118.86	64.152884	23235.32	1.0	125421
48	2022	12	16418548.14	63.093177	23949.46	1.0	260227

	acct_num	trans_month_year	category	age	gender	job	city	state	zip	trans_count	mean_amt	max_amt	min_amt	total_amt
0	2348758451	2018-12	gas_transport	42	M	Surveyor, minerals	Rochester	NY	14621	1	96.050000	96.05	96.05	96.05
1	2348758451	2019-01	gas_transport	42	M	Surveyor, minerals	Rochester	NY	14621	40	78.377750	359.87	5.67	3135.11
2	2348758451	2019-02	gas_transport	42	M	Surveyor, minerals	Rochester	NY	14621	49	62.837143	245.29	4.41	3079.02
3	2348758451	2019-03	gas_transport	42	M	Surveyor, minerals	Rochester	NY	14621	57	54.632456	131.91	1.73	3114.05
4	2348758451	2019-04	gas_transport	42	M	Surveyor, minerals	Rochester	NY	14621	60	69.893500	1183.46	1.27	4193.61

	acct_num	trans_month_year	category	age	gender	job	city	state	zip	trans_count	mean_amt	max_amt	min_amt	total_amt
48	2348758451	2022-12	travel	42	M	Surveyor, minerals	Rochester	NY	14621	285	47.048211	1562.15	1.10	13408.74
97	2468061102	2022-12	travel	60	F	Nurse, adult	Oceanside	CA	92057	310	61.225613	1748.31	1.02	18979.94
146	3005591724	2022-12	travel	73	F	Engineer, automotive	Lancaster	PA	17601	208	55.259808	384.94	1.05	11494.04
194	3418322859	2022-12	travel	17	F	Operational investment banker	Mountain View	CA	94040	286	56.277762	1928.42	1.01	16095.44
242	4322238535	2022-12	travel	88	M	Catering manager	Honolulu	HI	96816	120	61.369250	245.56	1.10	7364.31

	acct_num	total_amt', Period2018-12_M	total_amt', Period2019-01_M	total_amt', Period2019-02_M	total_amt', Period2019-03_M	total_amt', Period2019-04_M	total_amt', Period2019-05_M	total_amt', Period2019-06_M	total_amt', Period2019-07_M	total_amt', Period2019-08_M	total_amt', Period2019-09_M	total_amt', Period2019-10_M	total_amt', Period2019-11_M	total_amt', Period2019-12_M	total_amt', Period2020-01_M	total_amt', Period2020-02_M	total_amt', Period2020-03_M	total_amt', Period2020-04_M	total_amt', Period2020-05_M	total_amt', Period2020-06_M	total_amt', Period2020-07_M	total_amt', Period2020-08_M	total_amt', Period2020-09_M	total_amt', Period2020-10_M	total_amt', Period2020-11_M	total_amt', Period2020-12_M	total_amt', Period2021-01_M	total_amt', Period2021-02_M	total_amt', Period2021-03_M	total_amt', Period2021-04_M	total_amt', Period2021-05_M	total_amt', Period2021-06_M	total_amt', Period2021-07_M	total_amt', Period2021-08_M	total_amt', Period2021-09_M	total_amt', Period2021-10_M	total_amt', Period2021-11_M	total_amt', Period2021-12_M	total_amt', Period2022-01_M	total_amt', Period2022-02_M	total_amt', Period2022-03_M	total_amt', Period2022-04_M	total_amt', Period2022-05_M	total_amt', Period2022-06_M	total_amt', Period2022-07_M	total_amt', Period2022-08_M	total_amt', Period2022-09_M	total_amt', Period2022-10_M	total_amt', Period2022-11_M	trans_count', Period2018-12_M	trans_count', Period2019-01_M	trans_count', Period2019-02_M	trans_count', Period2019-03_M	trans_count', Period2019-04_M	trans_count', Period2019-05_M	trans_count', Period2019-06_M	trans_count', Period2019-07_M	trans_count', Period2019-08_M	trans_count', Period2019-09_M	trans_count', Period2019-10_M	trans_count', Period2019-11_M	trans_count', Period2019-12_M	trans_count', Period2020-01_M	trans_count', Period2020-02_M	trans_count', Period2020-03_M	trans_count', Period2020-04_M	trans_count', Period2020-05_M	trans_count', Period2020-06_M	trans_count', Period2020-07_M	trans_count', Period2020-08_M	trans_count', Period2020-09_M	trans_count', Period2020-10_M	trans_count', Period2020-11_M	trans_count', Period2020-12_M	trans_count', Period2021-01_M	trans_count', Period2021-02_M	trans_count', Period2021-03_M	trans_count', Period2021-04_M	trans_count', Period2021-05_M	trans_count', Period2021-06_M	trans_count', Period2021-07_M	trans_count', Period2021-08_M	trans_count', Period2021-09_M	trans_count', Period2021-10_M	trans_count', Period2021-11_M	trans_count', Period2021-12_M	trans_count', Period2022-01_M	trans_count', Period2022-02_M	trans_count', Period2022-03_M	trans_count', Period2022-04_M	trans_count', Period2022-05_M	trans_count', Period2022-06_M	trans_count', Period2022-07_M	trans_count', Period2022-08_M	trans_count', Period2022-09_M	trans_count', Period2022-10_M	trans_count', Period2022-11_M	trans_count', Period2022-12_M	age	job	city	age_group	Target	gender_F	gender_M
775	804015362037	0.00	3123.45	3105.97	5041.83	4733.73	5936.18	6003.54	6051.26	6367.30	4736.08	5356.48	3346.69	7675.86	6310.53	1377.63	3287.53	2139.62	3903.18	3003.03	4367.25	5236.80	6016.03	3291.25	4962.00	8367.57	2246.67	2179.63	5037.71	4771.50	4452.99	4557.49	3782.78	4488.08	6007.86	4082.10	6886.50	8889.13	3602.92	1668.74	2884.05	2848.66	2693.22	10212.05	2734.09	3644.57	2627.50	3793.83	2611.68	0	51	55	90	85	98	100	103	114	82	94	83	174	51	59	93	70	95	95	94	125	81	78	83	163	60	55	86	86	88	87	106	108	69	77	83	174	78	52	73	81	98	87	108	107	73	81	67	180	17	Social research officer, government	Alexandria	<18	9043.66	0.0	1.0
387	393298413208	835.23	13984.16	13072.89	22517.81	18581.44	19171.91	24378.44	23321.76	23096.50	16874.02	22011.31	21538.35	36467.39	13150.15	15694.78	19229.05	14852.31	14146.26	10714.28	17610.24	13843.86	11823.63	17891.55	11184.49	28122.69	8620.69	9220.63	11166.28	12700.94	13819.21	13263.25	15326.90	16453.47	12934.47	10507.25	12008.29	24896.22	23180.77	18767.65	30773.95	31211.25	30385.21	29784.23	31958.44	32422.40	22131.49	26061.62	27641.94	6	115	118	182	170	177	216	198	208	162	180	196	296	114	142	158	171	183	174	193	206	162	184	139	357	116	119	163	165	188	203	212	194	173	158	173	340	212	201	335	315	341	394	445	397	304	322	326	688	36	Museum/gallery curator	Martinsville	35-44	50099.15	1.0	0.0
875	904203673772	109.25	3874.83	3185.31	4219.23	4778.72	7488.23	4563.77	5527.70	6626.63	5529.02	5035.23	6595.74	14487.49	4720.18	4265.60	5156.29	4247.51	4456.70	6036.49	7903.62	6176.79	6025.58	4364.49	4731.12	11120.26	5251.95	2942.86	4276.94	6309.80	6372.30	4204.82	14146.69	6139.59	4948.50	4585.45	4052.23	11364.84	6114.07	9099.57	5951.29	9278.87	9831.60	10794.38	10221.10	19323.26	5951.54	8416.12	6541.68	1	62	56	77	81	74	91	93	111	76	89	90	166	66	59	88	78	80	92	127	103	84	80	87	175	56	59	75	74	84	78	101	113	90	73	74	174	105	104	133	157	149	162	157	177	125	147	137	306	47	Associate Professor	Columbus	45-54	16953.57	1.0	0.0
167	161262210869	515.56	3907.69	4115.90	6057.44	9166.64	8864.49	7783.45	6226.43	7784.48	4629.48	6979.59	5756.26	11488.76	4907.35	3380.40	5645.12	4390.19	6692.77	4651.44	5565.36	6438.19	4567.41	4067.22	7752.15	12125.93	5030.73	4221.51	3984.55	8278.41	7064.68	6136.51	5711.87	5072.22	3478.43	4534.57	5076.26	12793.79	7403.88	5764.70	10368.75	7900.36	9252.29	13011.26	8008.01	9496.38	6655.23	7850.18	7498.56	2	63	50	96	85	102	104	107	115	80	96	91	164	66	69	83	78	103	85	92	107	89	78	99	140	67	55	70	88	77	84	111	99	68	92	101	184	103	88	180	136	136	174	144	156	121	132	139	247	48	Sales professional, IT	Sherwood	45-54	12961.80	0.0	1.0
548	554990175020	309.46	2250.33	4034.83	4791.52	6821.45	5595.22	7270.58	6715.06	7131.95	4652.46	5181.26	3933.96	10511.21	3574.56	5213.22	3447.49	6180.09	5508.11	5619.60	6550.95	7972.92	6848.87	8116.71	4261.93	11158.79	5294.54	4128.81	6235.92	4698.01	6792.97	6638.87	6533.63	5404.85	4138.93	4173.73	5332.28	10626.88	2582.78	3340.69	8687.11	3793.95	4759.63	5033.70	4758.63	5631.71	4179.91	6404.53	6111.89	3	49	61	79	91	95	99	88	91	86	103	81	167	60	61	72	65	93	90	98	123	93	94	70	156	70	60	75	88	93	105	98	102	72	95	89	168	52	65	88	87	96	89	98	102	81	84	98	157	52	Acupuncturist	Forks	45-54	8897.78	1.0	0.0

	mae	mse	rmse
MultiLinear_Train	2079.423872	9.298125e+06	3049.282748
MultiLinear_Val	2267.698408	1.029542e+07	3208.647385

	mae	mse	rmse
MultiLinear_Feature1_Train	2070.482628	9.344101e+06	3056.812263
MultiLinear_Feature1_Val	2230.827601	1.010146e+07	3178.280116

	mae	mse	rmse
MultiLinear_Feature2_Train	2093.693198	1.030223e+07	3209.708360
MultiLinear_Feature2_Val	2123.415974	9.319224e+06	3052.740411

	mae	mse	rmse
MultiLinear_Feature3_Train	2278.747762	1.223434e+07	3497.762131
MultiLinear_Feature3_Val	2124.895843	9.739218e+06	3120.772055

	mae	mse	rmse
Baseline_Train	8307.422361	1.105862e+08	10515.995863
Baseline_Test	7751.203825	1.000556e+08	10002.777477
MultiLinear_Train	2079.423872	9.298125e+06	3049.282748
MultiLinear_Val	2267.698408	1.029542e+07	3208.647385
MultiLinear_Feature1_Train	2070.482628	9.344101e+06	3056.812263
MultiLinear_Feature1_Val	2230.827601	1.010146e+07	3178.280116
MultiLinear_Feature2_Train	2093.693198	1.030223e+07	3209.708360
MultiLinear_Feature2_Val	2123.415974	9.319224e+06	3052.740411
MultiLinear_Feature3_Train	2278.747762	1.223434e+07	3497.762131
MultiLinear_Feature3_Val	2124.895843	9.739218e+06	3120.772055

	mae	mse	rmse
Lasso_Train	2093.725380	9.353681e+06	3058.378796
Lasso_Val	2279.843057	1.024395e+07	3200.616371

	total_amt', Period2018-12_M	total_amt', Period2019-01_M	total_amt', Period2019-02_M	total_amt', Period2019-03_M	total_amt', Period2019-04_M	total_amt', Period2019-05_M	total_amt', Period2019-06_M	total_amt', Period2019-07_M	total_amt', Period2019-08_M	total_amt', Period2019-09_M	total_amt', Period2019-10_M	total_amt', Period2019-11_M	total_amt', Period2019-12_M	total_amt', Period2020-01_M	total_amt', Period2020-02_M	total_amt', Period2020-03_M	total_amt', Period2020-04_M	total_amt', Period2020-05_M	total_amt', Period2020-06_M	total_amt', Period2020-07_M	total_amt', Period2020-08_M	total_amt', Period2020-09_M	total_amt', Period2020-10_M	total_amt', Period2020-11_M	total_amt', Period2020-12_M	total_amt', Period2021-01_M	total_amt', Period2021-02_M	total_amt', Period2021-03_M	total_amt', Period2021-04_M	total_amt', Period2021-05_M	total_amt', Period2021-06_M	total_amt', Period2021-07_M	total_amt', Period2021-08_M	total_amt', Period2021-09_M	total_amt', Period2021-10_M	total_amt', Period2021-11_M	total_amt', Period2021-12_M	total_amt', Period2022-01_M	total_amt', Period2022-02_M	total_amt', Period2022-03_M	total_amt', Period2022-04_M	total_amt', Period2022-05_M	total_amt', Period2022-06_M	total_amt', Period2022-07_M	total_amt', Period2022-08_M	total_amt', Period2022-09_M	total_amt', Period2022-10_M	total_amt', Period2022-11_M	trans_count', Period2018-12_M	trans_count', Period2019-01_M	trans_count', Period2019-02_M	trans_count', Period2019-03_M	trans_count', Period2019-04_M	trans_count', Period2019-05_M	trans_count', Period2019-06_M	trans_count', Period2019-07_M	trans_count', Period2019-08_M	trans_count', Period2019-09_M	trans_count', Period2019-10_M	trans_count', Period2019-11_M	trans_count', Period2019-12_M	trans_count', Period2020-01_M	trans_count', Period2020-02_M	trans_count', Period2020-03_M	trans_count', Period2020-04_M	trans_count', Period2020-05_M	trans_count', Period2020-06_M	trans_count', Period2020-07_M	trans_count', Period2020-08_M	trans_count', Period2020-09_M	trans_count', Period2020-10_M	trans_count', Period2020-11_M	trans_count', Period2020-12_M	trans_count', Period2021-01_M	trans_count', Period2021-02_M	trans_count', Period2021-03_M	trans_count', Period2021-04_M	trans_count', Period2021-05_M	trans_count', Period2021-06_M	trans_count', Period2021-07_M	trans_count', Period2021-08_M	trans_count', Period2021-09_M	trans_count', Period2021-10_M	trans_count', Period2021-11_M	trans_count', Period2021-12_M	trans_count', Period2022-01_M	trans_count', Period2022-02_M	trans_count', Period2022-03_M	trans_count', Period2022-04_M	trans_count', Period2022-05_M	trans_count', Period2022-06_M	trans_count', Period2022-07_M	trans_count', Period2022-08_M	trans_count', Period2022-09_M	trans_count', Period2022-10_M	trans_count', Period2022-11_M	trans_count', Period2022-12_M	age	Target
total_amt', Period2018-12_M	1.000000	0.532484	0.522456	0.511195	0.530995	0.517475	0.529913	0.530591	0.521404	0.539699	0.535104	0.520855	0.523571	0.515719	0.529609	0.513539	0.485701	0.446822	0.445354	0.501977	0.477245	0.486197	0.466752	0.458473	0.505537	0.475332	0.415254	0.482738	0.477579	0.460709	0.461116	0.478910	0.475206	0.483292	0.476297	0.446306	0.471941	0.425631	0.423659	0.413413	0.420878	0.433582	0.408367	0.437908	0.399066	0.419300	0.393458	0.405663	0.758131	0.452343	0.462406	0.458912	0.468279	0.454956	0.462828	0.464256	0.456326	0.470820	0.459396	0.458764	0.461434	0.470286	0.475649	0.457420	0.453956	0.449220	0.464791	0.470284	0.468283	0.471719	0.454737	0.459383	0.472859	0.462823	0.441932	0.469830	0.460774	0.456129	0.464774	0.463455	0.463294	0.458722	0.466350	0.446187	0.463210	0.391451	0.396722	0.382438	0.384457	0.380524	0.390909	0.401394	0.383796	0.388190	0.382005	0.384506	0.386503	-0.183845	0.434274
total_amt', Period2019-01_M	0.532484	1.000000	0.916214	0.937136	0.938201	0.937005	0.944725	0.945612	0.947833	0.937074	0.938838	0.933687	0.949845	0.927369	0.914979	0.935022	0.856693	0.842186	0.808883	0.849753	0.835867	0.824464	0.821580	0.800321	0.875595	0.800278	0.773230	0.837261	0.801300	0.808359	0.837400	0.847710	0.778866	0.797004	0.834971	0.789355	0.866196	0.738596	0.723252	0.710342	0.727539	0.730376	0.716978	0.706839	0.712005	0.723632	0.685961	0.683284	0.469361	0.867305	0.827236	0.834492	0.837639	0.832431	0.842734	0.842286	0.843911	0.836527	0.843813	0.847733	0.845453	0.835428	0.840678	0.838266	0.831728	0.832231	0.843920	0.840544	0.832978	0.843401	0.831950	0.838680	0.850894	0.826641	0.825560	0.838643	0.828041	0.834356	0.837536	0.833660	0.835547	0.837525	0.839388	0.830636	0.838665	0.711435	0.688998	0.678354	0.681420	0.693669	0.698531	0.689756	0.689761	0.684164	0.692214	0.681917	0.691093	-0.314821	0.756122
total_amt', Period2019-02_M	0.522456	0.916214	1.000000	0.928625	0.933851	0.932109	0.938462	0.935318	0.933530	0.935102	0.935894	0.921929	0.936889	0.929482	0.906812	0.919464	0.854616	0.836868	0.801239	0.845848	0.824963	0.813410	0.814041	0.794866	0.864707	0.790995	0.767196	0.836871	0.796464	0.800576	0.832140	0.839360	0.790242	0.791644	0.824704	0.786317	0.869827	0.720941	0.714472	0.697890	0.707402	0.716387	0.700699	0.696530	0.703610	0.710236	0.670724	0.671849	0.462963	0.821353	0.870161	0.830100	0.834151	0.828582	0.838449	0.836692	0.833723	0.835141	0.837570	0.837294	0.837470	0.841366	0.830363	0.831369	0.826092	0.831807	0.837182	0.835129	0.827187	0.833601	0.825370	0.834284	0.843543	0.821560	0.816118	0.829301	0.819529	0.829209	0.833878	0.829774	0.835839	0.831459	0.833806	0.827235	0.834301	0.692535	0.673323	0.661588	0.663667	0.677460	0.675784	0.674317	0.670360	0.668236	0.671368	0.666378	0.672320	-0.308327	0.736216
total_amt', Period2019-03_M	0.511195	0.937136	0.928625	1.000000	0.944329	0.946561	0.953934	0.955878	0.952494	0.944929	0.949748	0.942166	0.952763	0.929830	0.914640	0.936724	0.866597	0.849458	0.812309	0.860593	0.849638	0.835887	0.828208	0.827572	0.877416	0.800524	0.781997	0.842405	0.809728	0.821268	0.847173	0.841998	0.788268	0.807852	0.843001	0.787829	0.878504	0.744890	0.729361	0.718262	0.728907	0.732597	0.720922	0.711025	0.717676	0.725661	0.692241	0.684701	0.468197	0.835327	0.837044	0.870714	0.844074	0.842022	0.852381	0.850870	0.849431	0.848160	0.852769	0.854246	0.852151	0.848167	0.844247	0.847701	0.845664	0.844811	0.850482	0.848804	0.844382	0.853677	0.837464	0.849299	0.856097	0.829909	0.829020	0.845552	0.834987	0.847176	0.846073	0.839410	0.845161	0.849971	0.845954	0.834370	0.849719	0.712484	0.689472	0.680758	0.683252	0.694329	0.697214	0.688379	0.690341	0.682826	0.691742	0.687030	0.691127	-0.317154	0.754889
total_amt', Period2019-04_M	0.530995	0.938201	0.933851	0.944329	1.000000	0.951047	0.951196	0.955496	0.950751	0.947074	0.947989	0.943317	0.954231	0.935805	0.913551	0.941970	0.870734	0.851876	0.816102	0.860193	0.849607	0.833377	0.834691	0.821159	0.879438	0.801753	0.783943	0.841836	0.817693	0.820705	0.845892	0.850282	0.785117	0.794618	0.845026	0.782626	0.876798	0.754006	0.736801	0.723432	0.741517	0.742116	0.720047	0.721130	0.720828	0.729735	0.703767	0.687573	0.466034	0.835619	0.840877	0.843371	0.874956	0.845523	0.852257	0.850693	0.849340	0.846332	0.852477	0.855461	0.852981	0.850313	0.844559	0.850761	0.842492	0.843618	0.851377	0.849786	0.844117	0.852200	0.839617	0.848311	0.857726	0.836577	0.830156	0.841997	0.836232	0.846324	0.846305	0.841950	0.845408	0.845724	0.847967	0.835301	0.846067	0.720980	0.698612	0.691083	0.691615	0.703747	0.701992	0.698905	0.698208	0.690579	0.701867	0.694853	0.699185	-0.318468	0.760828
total_amt', Period2019-05_M	0.517475	0.937005	0.932109	0.946561	0.951047	1.000000	0.953899	0.953930	0.955459	0.946753	0.951378	0.944847	0.957814	0.939190	0.920633	0.939572	0.865240	0.845355	0.823189	0.857898	0.849753	0.841499	0.837901	0.821685	0.881403	0.800141	0.780155	0.840020	0.811467	0.820852	0.845813	0.855812	0.792227	0.808272	0.844530	0.797268	0.880724	0.747312	0.735611	0.716229	0.738930	0.736502	0.731702	0.715696	0.720976	0.726998	0.699281	0.687091	0.465663	0.841041	0.842734	0.847101	0.849373	0.873533	0.854790	0.853106	0.854924	0.850055	0.856715	0.857707	0.858691	0.853196	0.848352	0.849106	0.845087	0.846251	0.854238	0.853096	0.846604	0.858116	0.844983	0.852801	0.861938	0.835303	0.836149	0.846114	0.837999	0.852313	0.847810	0.846822	0.849642	0.849384	0.850287	0.842099	0.852541	0.720615	0.699520	0.687619	0.693059	0.703482	0.705345	0.700335	0.699899	0.690638	0.701191	0.692597	0.699547	-0.320345	0.762687
total_amt', Period2019-06_M	0.529913	0.944725	0.938462	0.953934	0.951196	0.953899	1.000000	0.962359	0.960953	0.956463	0.953610	0.951268	0.963040	0.942800	0.930568	0.941453	0.876298	0.853907	0.817987	0.863368	0.848563	0.836587	0.833242	0.824595	0.879509	0.804130	0.782277	0.846208	0.810119	0.823106	0.847522	0.850500	0.794651	0.814241	0.843420	0.791439	0.886241	0.749527	0.737941	0.718949	0.739820	0.737101	0.720356	0.714604	0.719936	0.725851	0.694761	0.691536	0.468306	0.840378	0.838535	0.846845	0.845405	0.844163	0.874446	0.852801	0.851066	0.848782	0.851791	0.857041	0.854831	0.847633	0.848464	0.846618	0.842380	0.845728	0.856488	0.851485	0.844402	0.851387	0.841978	0.850541	0.858753	0.833486	0.832801	0.846650	0.834347	0.845410	0.846228	0.842755	0.848757	0.846544	0.850755	0.837605	0.848754	0.714582	0.693278	0.683926	0.686240	0.697467	0.698274	0.694527	0.693276	0.684839	0.695884	0.688481	0.693433	-0.327645	0.758815
total_amt', Period2019-07_M	0.530591	0.945612	0.935318	0.955878	0.955496	0.953930	0.962359	1.000000	0.960179	0.953639	0.955936	0.951293	0.963679	0.939604	0.928270	0.948570	0.872090	0.856496	0.817224	0.862849	0.851660	0.843389	0.842050	0.825836	0.882305	0.805844	0.788315	0.846252	0.817480	0.818173	0.849906	0.858493	0.787473	0.814664	0.851908	0.796234	0.884223	0.752446	0.739745	0.725418	0.745081	0.744286	0.723619	0.726857	0.726148	0.730342	0.707365	0.697302	0.478752	0.841287	0.841762	0.848015	0.847243	0.845775	0.857282	0.876209	0.850850	0.850547	0.853757	0.859127	0.857003	0.851245	0.848025	0.852657	0.844680	0.847354	0.857067	0.853267	0.845227	0.856910	0.842750	0.854140	0.860508	0.833541	0.834782	0.846012	0.837847	0.850273	0.848157	0.844969	0.848376	0.849497	0.852688	0.838165	0.852593	0.718733	0.700187	0.690842	0.692114	0.703907	0.705526	0.702023	0.700026	0.693268	0.703741	0.692095	0.700103	-0.330162	0.767414
total_amt', Period2019-08_M	0.521404	0.947833	0.933530	0.952494	0.950751	0.955459	0.960953	0.960179	1.000000	0.954425	0.955215	0.949453	0.961861	0.943884	0.927275	0.943664	0.869102	0.850315	0.823379	0.862467	0.846218	0.836732	0.831373	0.821638	0.884477	0.808699	0.792435	0.846651	0.820024	0.819695	0.852928	0.863354	0.789950	0.810299	0.851879	0.793491	0.891064	0.748756	0.734571	0.710101	0.731262	0.734056	0.716172	0.715725	0.715935	0.725794	0.694738	0.690413	0.467535	0.843100	0.840316	0.848133	0.846596	0.845386	0.857034	0.853536	0.872691	0.852616	0.852823	0.858899	0.856632	0.854692	0.850126	0.850201	0.845209	0.845661	0.856239	0.853515	0.845346	0.856603	0.841874	0.855877	0.860508	0.834926	0.836035	0.847280	0.837990	0.849375	0.849608	0.845519	0.849981	0.851840	0.851657	0.838768	0.852516	0.715572	0.692499	0.680239	0.683681	0.696728	0.694803	0.692115	0.691264	0.685406	0.693420	0.685243	0.691406	-0.318723	0.757570
total_amt', Period2019-09_M	0.539699	0.937074	0.935102	0.944929	0.947074	0.946753	0.956463	0.953639	0.954425	1.000000	0.953389	0.943442	0.954467	0.932251	0.919621	0.935227	0.866395	0.844398	0.817040	0.857196	0.839314	0.841009	0.837542	0.819573	0.875705	0.809148	0.775294	0.840272	0.809211	0.813777	0.840542	0.849302	0.780298	0.799661	0.844426	0.787031	0.876235	0.748833	0.734449	0.715830	0.737366	0.736075	0.723171	0.719929	0.712678	0.726541	0.698218	0.684080	0.484111	0.834109	0.839286	0.843196	0.840499	0.841219	0.849991	0.847656	0.848204	0.872030	0.851707	0.850842	0.849773	0.845091	0.843241	0.842754	0.837955	0.840443	0.848818	0.848264	0.842051	0.853002	0.839597	0.845751	0.854474	0.833616	0.824318	0.840854	0.833288	0.842423	0.842850	0.841096	0.844746	0.842654	0.846919	0.833687	0.846134	0.717429	0.694365	0.682877	0.688189	0.696022	0.697622	0.696155	0.692092	0.685192	0.695329	0.687185	0.694720	-0.324954	0.761886
total_amt', Period2019-10_M	0.535104	0.938838	0.935894	0.949748	0.947989	0.951378	0.953610	0.955936	0.955215	0.953389	1.000000	0.943223	0.956162	0.936699	0.923176	0.939573	0.861699	0.844712	0.815067	0.862132	0.845172	0.839838	0.837094	0.818562	0.881798	0.804190	0.780733	0.841768	0.814384	0.809214	0.847662	0.848022	0.790080	0.805233	0.837020	0.788109	0.878820	0.746373	0.727265	0.713202	0.731437	0.733245	0.716529	0.714106	0.716521	0.719490	0.690752	0.684669	0.482206	0.839741	0.842873	0.847223	0.846124	0.846933	0.854744	0.852597	0.852617	0.852242	0.875611	0.856160	0.855043	0.854185	0.847986	0.848301	0.841783	0.844232	0.853699	0.850074	0.845952	0.857104	0.841540	0.851632	0.859154	0.833951	0.831182	0.846880	0.837649	0.845420	0.847209	0.843144	0.847269	0.845240	0.851644	0.835088	0.848271	0.715502	0.686305	0.681231	0.682674	0.695304	0.697443	0.692981	0.692508	0.681990	0.692692	0.686582	0.691326	-0.317660	0.754560
total_amt', Period2019-11_M	0.520855	0.933687	0.921929	0.942166	0.943317	0.944847	0.951268	0.951293	0.949453	0.943442	0.943223	1.000000	0.955128	0.931295	0.926052	0.936454	0.865690	0.845800	0.806814	0.852161	0.834909	0.838404	0.826590	0.811670	0.870316	0.787800	0.775049	0.836132	0.805849	0.810927	0.840910	0.844699	0.778445	0.799951	0.835893	0.783851	0.870674	0.751966	0.737661	0.714785	0.740507	0.739898	0.722863	0.722330	0.721674	0.722827	0.701690	0.689194	0.467490	0.822596	0.822838	0.830398	0.831155	0.828212	0.839350	0.838255	0.836124	0.834853	0.835944	0.867190	0.841385	0.833898	0.836569	0.833486	0.827109	0.829316	0.838042	0.837108	0.827290	0.843653	0.824964	0.835540	0.844236	0.819112	0.818102	0.831175	0.824937	0.832278	0.833911	0.829447	0.833690	0.833769	0.832424	0.823108	0.835341	0.709497	0.686723	0.678714	0.686633	0.692764	0.694308	0.691582	0.689957	0.679749	0.695174	0.684785	0.689249	-0.312195	0.754430
total_amt', Period2019-12_M	0.523571	0.949845	0.936889	0.952763	0.954231	0.957814	0.963040	0.963679	0.961861	0.954467	0.956162	0.955128	1.000000	0.950758	0.937170	0.946857	0.869203	0.860004	0.826300	0.866345	0.850771	0.842283	0.837709	0.829413	0.888700	0.803908	0.785557	0.850956	0.818786	0.822693	0.848562	0.857952	0.782097	0.808274	0.839210	0.799571	0.888657	0.761777	0.751094	0.728168	0.749447	0.753157	0.734642	0.732053	0.730632	0.740601	0.710046	0.704329	0.472337	0.838494	0.837416	0.840928	0.842828	0.840135	0.850908	0.849921	0.847840	0.844658	0.852335	0.854351	0.864487	0.849414	0.845170	0.846034	0.841669	0.841110	0.853370	0.850083	0.841418	0.852952	0.838939	0.850622	0.858225	0.830021	0.830879	0.843387	0.835539	0.845257	0.845331	0.840239	0.844223	0.845563	0.844685	0.835941	0.847102	0.723941	0.703548	0.692590	0.696505	0.708274	0.710196	0.703130	0.704423	0.695758	0.706967	0.699163	0.703618	-0.313784	0.771768
total_amt', Period2020-01_M	0.515719	0.927369	0.929482	0.929830	0.935805	0.939190	0.942800	0.939604	0.943884	0.932251	0.936699	0.931295	0.950758	1.000000	0.914126	0.929508	0.844622	0.838016	0.813749	0.843616	0.836454	0.828022	0.819903	0.810374	0.865941	0.796519	0.767838	0.837059	0.799749	0.798877	0.833320	0.837513	0.778458	0.805156	0.828551	0.774327	0.867870	0.739898	0.727243	0.707702	0.728251	0.733149	0.714429	0.707699	0.707351	0.724894	0.688702	0.687473	0.449970	0.813013	0.818792	0.813338	0.817815	0.813124	0.825166	0.820867	0.822599	0.819227	0.823674	0.824633	0.824816	0.856438	0.818418	0.819095	0.812018	0.815993	0.829243	0.820633	0.814795	0.827514	0.811494	0.822874	0.830157	0.809665	0.803133	0.820457	0.811332	0.815117	0.819760	0.815666	0.818845	0.821093	0.821475	0.808098	0.823219	0.700432	0.675948	0.664802	0.666009	0.681234	0.677933	0.677273	0.675784	0.668616	0.675463	0.667332	0.675469	-0.305790	0.752379
total_amt', Period2020-02_M	0.529609	0.914979	0.906812	0.914640	0.913551	0.920633	0.930568	0.928270	0.927275	0.919621	0.923176	0.926052	0.937170	0.914126	1.000000	0.916429	0.853743	0.839630	0.809091	0.847194	0.812164	0.820546	0.815475	0.790512	0.860183	0.784185	0.769357	0.830238	0.809469	0.793411	0.837313	0.836509	0.766017	0.786983	0.824944	0.790430	0.868080	0.737732	0.723896	0.703950	0.730249	0.728000	0.719419	0.716416	0.710895	0.717045	0.691949	0.680069	0.469047	0.805934	0.812655	0.808823	0.812738	0.811102	0.819685	0.819231	0.818147	0.818629	0.819330	0.826910	0.823534	0.821145	0.859851	0.816803	0.817136	0.817325	0.825514	0.823889	0.813063	0.823819	0.808763	0.819418	0.829180	0.808745	0.809038	0.820969	0.812729	0.821374	0.824557	0.816931	0.820168	0.821949	0.823526	0.812496	0.823028	0.699454	0.680356	0.667740	0.674279	0.681749	0.685305	0.678660	0.676305	0.671894	0.683872	0.670156	0.675368	-0.291454	0.748464
total_amt', Period2020-03_M	0.513539	0.935022	0.919464	0.936724	0.941970	0.939572	0.941453	0.948570	0.943664	0.935227	0.939573	0.936454	0.946857	0.929508	0.916429	1.000000	0.859649	0.851601	0.809412	0.845353	0.836106	0.832415	0.816521	0.805156	0.877783	0.802319	0.788457	0.843919	0.810127	0.827840	0.842586	0.846562	0.788282	0.801736	0.836418	0.785224	0.869897	0.752503	0.733344	0.718754	0.731418	0.738159	0.715960	0.714486	0.723762	0.734158	0.702185	0.693752	0.464206	0.829202	0.823799	0.825855	0.831412	0.826711	0.834914	0.836654	0.834789	0.831284	0.834757	0.839552	0.835840	0.832837	0.833949	0.859817	0.829212	0.829420	0.840067	0.832099	0.827833	0.839180	0.823068	0.831793	0.846524	0.822310	0.818005	0.831303	0.822874	0.835737	0.834130	0.826848	0.833697	0.831932	0.831107	0.824353	0.836989	0.709346	0.685964	0.677049	0.678187	0.691315	0.688463	0.686814	0.686971	0.679282	0.691428	0.682229	0.687648	-0.316831	0.762595
total_amt', Period2020-04_M	0.485701	0.856693	0.854616	0.866597	0.870734	0.865240	0.876298	0.872090	0.869102	0.866395	0.861699	0.865690	0.869203	0.844622	0.853743	0.859649	1.000000	0.840989	0.801433	0.847051	0.834523	0.828472	0.822152	0.811324	0.866366	0.798959	0.773993	0.838165	0.807955	0.812166	0.835395	0.838280	0.766574	0.782726	0.832518	0.773285	0.859573	0.674635	0.644672	0.631092	0.657191	0.669268	0.672347	0.657171	0.667004	0.674628	0.646981	0.627969	0.485464	0.850917	0.849549	0.852736	0.860531	0.851263	0.862802	0.860017	0.858073	0.855195	0.855024	0.864256	0.855792	0.854218	0.858991	0.855590	0.888219	0.856457	0.863245	0.861838	0.855086	0.860032	0.853030	0.859128	0.866113	0.850791	0.854158	0.861158	0.853805	0.858827	0.855394	0.858764	0.861111	0.859388	0.861739	0.853786	0.862990	0.697603	0.669698	0.657860	0.666771	0.675192	0.673857	0.670431	0.666265	0.660779	0.674390	0.661446	0.671346	-0.248190	0.697025
total_amt', Period2020-05_M	0.446822	0.842186	0.836868	0.849458	0.851876	0.845355	0.853907	0.856496	0.850315	0.844398	0.844712	0.845800	0.860004	0.838016	0.839630	0.851601	0.840989	1.000000	0.806343	0.847871	0.837474	0.813473	0.816868	0.813686	0.861713	0.804348	0.781152	0.826486	0.818018	0.810488	0.834491	0.832271	0.775290	0.795886	0.824940	0.776832	0.859753	0.657608	0.632602	0.603902	0.630553	0.644195	0.652644	0.645686	0.659361	0.657596	0.637444	0.613387	0.479081	0.864858	0.864501	0.867290	0.869178	0.863429	0.874092	0.876971	0.869166	0.866643	0.865995	0.873185	0.877885	0.869979	0.873607	0.873574	0.878455	0.893951	0.877946	0.871269	0.867331	0.866935	0.865063	0.874658	0.877283	0.868204	0.858249	0.863834	0.870206	0.869265	0.869753	0.872193	0.881120	0.875106	0.872996	0.864882	0.879445	0.699806	0.673265	0.662994	0.664106	0.678629	0.679130	0.669480	0.670035	0.673062	0.675682	0.666054	0.674330	-0.280079	0.709183
total_amt', Period2020-06_M	0.445354	0.808883	0.801239	0.812309	0.816102	0.823189	0.817987	0.817224	0.823379	0.817040	0.815067	0.806814	0.826300	0.813749	0.809091	0.809412	0.801433	0.806343	1.000000	0.824093	0.790245	0.784600	0.793989	0.776071	0.844297	0.776442	0.747498	0.795729	0.778834	0.770877	0.796804	0.797548	0.749587	0.745775	0.794994	0.744705	0.829917	0.623147	0.606901	0.585160	0.608398	0.621053	0.645636	0.629752	0.619612	0.638981	0.614928	0.605353	0.472909	0.831444	0.823604	0.827087	0.832778	0.835224	0.834572	0.832209	0.835806	0.834563	0.836785	0.836454	0.837656	0.844153	0.831936	0.835972	0.835339	0.832715	0.866434	0.842639	0.837935	0.832636	0.831023	0.836407	0.843585	0.833885	0.825870	0.836477	0.831869	0.835499	0.835679	0.829580	0.836382	0.834678	0.845524	0.832502	0.841700	0.679121	0.654875	0.643607	0.647125	0.660406	0.663682	0.656154	0.650962	0.647449	0.656761	0.647089	0.655558	-0.253134	0.672751
total_amt', Period2020-07_M	0.501977	0.849753	0.845848	0.860593	0.860193	0.857898	0.863368	0.862849	0.862467	0.857196	0.862132	0.852161	0.866345	0.843616	0.847194	0.845353	0.847051	0.847871	0.824093	1.000000	0.848807	0.823132	0.835570	0.819269	0.864159	0.792638	0.793667	0.836056	0.825752	0.801458	0.843469	0.835033	0.781385	0.783119	0.827048	0.784321	0.856908	0.659585	0.637151	0.614829	0.635527	0.645198	0.662911	0.666026	0.652286	0.662503	0.640796	0.640435	0.510456	0.862340	0.862528	0.872208	0.872781	0.860464	0.875285	0.867922	0.873284	0.870173	0.872540	0.875436	0.870269	0.870584	0.871446	0.867747	0.872674	0.870352	0.878817	0.901283	0.867992	0.872829	0.864773	0.871239	0.876992	0.863269	0.860332	0.872952	0.866749	0.866498	0.871740	0.865096	0.874206	0.870715	0.874834	0.866862	0.877744	0.703439	0.671278	0.666287	0.663314	0.678809	0.675417	0.671938	0.668603	0.667312	0.674469	0.667621	0.673420	-0.250594	0.701580
total_amt', Period2020-08_M	0.477245	0.835867	0.824963	0.849638	0.849607	0.849753	0.848563	0.851660	0.846218	0.839314	0.845172	0.834909	0.850771	0.836454	0.812164	0.836106	0.834523	0.837474	0.790245	0.848807	1.000000	0.806364	0.820203	0.816261	0.852551	0.799862	0.773943	0.822494	0.823116	0.794878	0.838124	0.832145	0.776504	0.774239	0.820864	0.762720	0.856917	0.658404	0.628213	0.614694	0.630875	0.652513	0.656614	0.652862	0.657128	0.659793	0.632172	0.621899	0.501250	0.867221	0.862084	0.872678	0.871187	0.869819	0.874352	0.878364	0.874050	0.868886	0.876637	0.877776	0.877918	0.876997	0.865883	0.875042	0.871847	0.872896	0.878615	0.877998	0.900458	0.879377	0.867329	0.877149	0.880929	0.870218	0.867196	0.877207	0.870659	0.871851	0.870259	0.876273	0.879403	0.870947	0.878606	0.868488	0.881406	0.710189	0.680931	0.677098	0.674186	0.686733	0.684657	0.680064	0.678642	0.679077	0.684896	0.673862	0.681997	-0.262369	0.694828
total_amt', Period2020-09_M	0.486197	0.824464	0.813410	0.835887	0.833377	0.841499	0.836587	0.843389	0.836732	0.841009	0.839838	0.838404	0.842283	0.828022	0.820546	0.832415	0.828472	0.813473	0.784600	0.823132	0.806364	1.000000	0.802783	0.783222	0.847025	0.780185	0.749586	0.822932	0.789009	0.778451	0.818017	0.824686	0.768973	0.778712	0.806085	0.740755	0.838687	0.671684	0.648304	0.621175	0.657036	0.662651	0.686581	0.654940	0.666492	0.664407	0.635497	0.635092	0.490791	0.834040	0.832155	0.843911	0.842371	0.845875	0.850917	0.850918	0.846457	0.848898	0.846841	0.850451	0.847964	0.851757	0.846598	0.847050	0.849668	0.842475	0.854636	0.851212	0.845916	0.882716	0.841136	0.843593	0.857063	0.836720	0.830926	0.854235	0.844610	0.843989	0.849042	0.853595	0.853383	0.848028	0.845503	0.835618	0.856426	0.704659	0.675514	0.669384	0.675292	0.682876	0.683377	0.678496	0.678743	0.674979	0.683370	0.672602	0.677314	-0.263945	0.693890
total_amt', Period2020-10_M	0.466752	0.821580	0.814041	0.828208	0.834691	0.837901	0.833242	0.842050	0.831373	0.837542	0.837094	0.826590	0.837709	0.819903	0.815475	0.816521	0.822152	0.816868	0.793989	0.835570	0.820203	0.802783	1.000000	0.793756	0.851424	0.773435	0.770448	0.817261	0.815349	0.780432	0.818086	0.815409	0.756906	0.780611	0.823262	0.768379	0.840438	0.640238	0.635065	0.598678	0.616873	0.624113	0.643810	0.642746	0.630037	0.639901	0.625242	0.609468	0.485507	0.847965	0.845926	0.852320	0.853066	0.856400	0.857115	0.862387	0.857710	0.863365	0.860262	0.865578	0.859502	0.861607	0.856971	0.853675	0.858267	0.856794	0.862192	0.864724	0.856583	0.866177	0.891589	0.856815	0.863899	0.847512	0.853544	0.856093	0.860606	0.855702	0.863612	0.859499	0.853258	0.859555	0.859741	0.856345	0.863875	0.685613	0.663714	0.650814	0.653688	0.657781	0.662728	0.657600	0.659911	0.654772	0.662381	0.653144	0.658319	-0.236607	0.674775
total_amt', Period2020-11_M	0.458473	0.800321	0.794866	0.827572	0.821159	0.821685	0.824595	0.825836	0.821638	0.819573	0.818562	0.811670	0.829413	0.810374	0.790512	0.805156	0.811324	0.813686	0.776071	0.819269	0.816261	0.783222	0.793756	1.000000	0.826117	0.765628	0.751847	0.804346	0.795276	0.776687	0.815931	0.816836	0.746658	0.743482	0.800522	0.730007	0.837022	0.643298	0.617644	0.596428	0.619163	0.645709	0.653662	0.637574	0.640429	0.644054	0.643198	0.607116	0.482933	0.827033	0.823170	0.839549	0.838775	0.836375	0.845160	0.843069	0.835894	0.843875	0.838072	0.842200	0.841384	0.839261	0.832610	0.840949	0.834632	0.838791	0.849870	0.843759	0.839161	0.849412	0.830690	0.876984	0.844049	0.834519	0.824016	0.845602	0.836483	0.838458	0.847664	0.839343	0.842186	0.836770	0.846757	0.832861	0.848910	0.693071	0.664956	0.659089	0.657854	0.674329	0.669810	0.666289	0.663248	0.656360	0.667404	0.652119	0.668906	-0.257556	0.689751
total_amt', Period2020-12_M	0.505537	0.875595	0.864707	0.877416	0.879438	0.881403	0.879509	0.882305	0.884477	0.875705	0.881798	0.870316	0.888700	0.865941	0.860183	0.877783	0.866366	0.861713	0.844297	0.864159	0.852551	0.847025	0.851424	0.826117	1.000000	0.815409	0.803312	0.857624	0.839505	0.823415	0.865175	0.863391	0.790196	0.806318	0.836247	0.799932	0.883340	0.670343	0.645004	0.618703	0.645347	0.655855	0.682345	0.666876	0.672354	0.660114	0.648611	0.640331	0.513899	0.885136	0.884840	0.884587	0.890986	0.887294	0.891971	0.892698	0.892099	0.889714	0.896240	0.894014	0.896682	0.891403	0.883090	0.893379	0.893720	0.886409	0.891179	0.893655	0.890150	0.896164	0.891328	0.893927	0.920369	0.879853	0.882983	0.895722	0.888803	0.890501	0.895285	0.891745	0.890474	0.891990	0.893257	0.885006	0.896249	0.712751	0.681482	0.673947	0.679059	0.688090	0.688169	0.681234	0.680155	0.674944	0.684281	0.676305	0.682646	-0.266159	0.706695
total_amt', Period2021-01_M	0.475332	0.800278	0.790995	0.800524	0.801753	0.800141	0.804130	0.805844	0.808699	0.809148	0.804190	0.787800	0.803908	0.796519	0.784185	0.802319	0.798959	0.804348	0.776442	0.792638	0.799862	0.780185	0.773435	0.765628	0.815409	1.000000	0.753068	0.795844	0.789011	0.761779	0.814013	0.796879	0.760450	0.754640	0.792968	0.759878	0.828306	0.653574	0.620659	0.593945	0.616883	0.635610	0.649472	0.657766	0.655386	0.672920	0.638459	0.621594	0.498540	0.826927	0.822855	0.828691	0.828320	0.828446	0.831176	0.833155	0.831994	0.836803	0.831566	0.826846	0.836362	0.833559	0.828894	0.836179	0.832967	0.834465	0.842782	0.835311	0.840271	0.837671	0.827259	0.834488	0.840067	0.875907	0.834174	0.835654	0.838788	0.836818	0.843795	0.838308	0.838745	0.842528	0.835343	0.833453	0.838157	0.698680	0.675285	0.666183	0.662207	0.673722	0.676060	0.678518	0.672926	0.670954	0.678259	0.668173	0.673478	-0.287751	0.688967
total_amt', Period2021-02_M	0.415254	0.773230	0.767196	0.781997	0.783943	0.780155	0.782277	0.788315	0.792435	0.775294	0.780733	0.775049	0.785557	0.767838	0.769357	0.788457	0.773993	0.781152	0.747498	0.793667	0.773943	0.749586	0.770448	0.751847	0.803312	0.753068	1.000000	0.793621	0.766442	0.746870	0.794749	0.776078	0.743634	0.722422	0.770963	0.718047	0.815118	0.606273	0.574141	0.561752	0.581066	0.599953	0.602978	0.605969	0.619095	0.608305	0.602918	0.587923	0.453495	0.810037	0.811205	0.816737	0.817614	0.809714	0.819773	0.819775	0.827147	0.818336	0.814980	0.818779	0.819606	0.817766	0.811999	0.824670	0.817253	0.813023	0.820866	0.824153	0.814214	0.820814	0.811606	0.815329	0.823971	0.810237	0.857156	0.826597	0.822809	0.816305	0.825359	0.817188	0.820443	0.825624	0.822236	0.814392	0.826159	0.657298	0.624002	0.622298	0.620498	0.631581	0.627268	0.626695	0.625790	0.625327	0.630377	0.617407	0.621871	-0.256310	0.638166
total_amt', Period2021-03_M	0.482738	0.837261	0.836871	0.842405	0.841836	0.840020	0.846208	0.846252	0.846651	0.840272	0.841768	0.836132	0.850956	0.837059	0.830238	0.843919	0.838165	0.826486	0.795729	0.836056	0.822494	0.822932	0.817261	0.804346	0.857624	0.795844	0.793621	1.000000	0.816650	0.802094	0.829238	0.833204	0.771792	0.775037	0.830704	0.770031	0.851767	0.660021	0.635524	0.627351	0.643777	0.657956	0.677890	0.663152	0.666305	0.667574	0.653069	0.645942	0.497957	0.848762	0.853107	0.853374	0.854308	0.848513	0.860435	0.858640	0.857949	0.854747	0.852611	0.858948	0.859462	0.861288	0.855663	0.858192	0.860176	0.854299	0.862440	0.858998	0.854820	0.864524	0.848891	0.855297	0.862997	0.853340	0.850078	0.887800	0.854594	0.858874	0.862108	0.857279	0.857385	0.855611	0.861903	0.854579	0.863449	0.706977	0.677974	0.674358	0.674833	0.686381	0.686826	0.682636	0.677295	0.675826	0.680370	0.673343	0.682048	-0.264663	0.711260
total_amt', Period2021-04_M	0.477579	0.801300	0.796464	0.809728	0.817693	0.811467	0.810119	0.817480	0.820024	0.809211	0.814384	0.805849	0.818786	0.799749	0.809469	0.810127	0.807955	0.818018	0.778834	0.825752	0.823116	0.789009	0.815349	0.795276	0.839505	0.789011	0.766442	0.816650	1.000000	0.784325	0.821260	0.808775	0.762056	0.761180	0.810708	0.759477	0.839062	0.627065	0.587097	0.566314	0.583734	0.612427	0.617552	0.614708	0.634151	0.627048	0.596953	0.606619	0.492438	0.833457	0.832401	0.838989	0.844775	0.840916	0.843816	0.844805	0.845663	0.845130	0.845672	0.851205	0.845918	0.844403	0.845624	0.846180	0.846650	0.850693	0.851523	0.846847	0.849836	0.848851	0.841230	0.847128	0.853788	0.841850	0.841145	0.844547	0.878431	0.846598	0.852480	0.844497	0.850550	0.849588	0.852824	0.843407	0.852731	0.675977	0.637803	0.636735	0.632547	0.649073	0.643742	0.639502	0.646275	0.634655	0.644966	0.633539	0.643505	-0.265520	0.666261
total_amt', Period2021-05_M	0.460709	0.808359	0.800576	0.821268	0.820705	0.820852	0.823106	0.818173	0.819695	0.813777	0.809214	0.810927	0.822693	0.798877	0.793411	0.827840	0.812166	0.810488	0.770877	0.801458	0.794878	0.778451	0.780432	0.776687	0.823415	0.761779	0.746870	0.802094	0.784325	1.000000	0.810763	0.800745	0.740192	0.753670	0.786160	0.737556	0.832624	0.645610	0.608060	0.606820	0.624844	0.632315	0.652936	0.644667	0.659245	0.637699	0.635143	0.609416	0.477867	0.821174	0.820285	0.834354	0.829801	0.825002	0.835081	0.831893	0.834351	0.830942	0.823723	0.832225	0.835571	0.829002	0.824469	0.834639	0.839882	0.835133	0.841168	0.833140	0.829678	0.826085	0.828289	0.835415	0.838782	0.825547	0.829252	0.833328	0.825350	0.864922	0.835499	0.830185	0.841012	0.829128	0.835904	0.827985	0.840924	0.682073	0.651841	0.645395	0.651801	0.658279	0.660551	0.656361	0.653789	0.646701	0.662196	0.651326	0.658233	-0.281386	0.678258
total_amt', Period2021-06_M	0.461116	0.837400	0.832140	0.847173	0.845892	0.845813	0.847522	0.849906	0.852928	0.840542	0.847662	0.840910	0.848562	0.833320	0.837313	0.842586	0.835395	0.834491	0.796804	0.843469	0.838124	0.818017	0.818086	0.815931	0.865175	0.814013	0.794749	0.829238	0.821260	0.810763	1.000000	0.840568	0.781678	0.802595	0.830789	0.774766	0.867800	0.675497	0.632633	0.613937	0.639062	0.651142	0.666822	0.670441	0.682974	0.668824	0.651563	0.629076	0.492030	0.867395	0.872866	0.875990	0.879482	0.873069	0.880029	0.879515	0.882775	0.875472	0.877032	0.882089	0.883489	0.885047	0.878974	0.886203	0.884154	0.885528	0.889857	0.883911	0.882278	0.885690	0.878975	0.883382	0.890442	0.879342	0.879574	0.887600	0.882491	0.884063	0.912472	0.884522	0.886666	0.887948	0.887688	0.879331	0.891030	0.727882	0.692078	0.691239	0.695940	0.699393	0.699280	0.693067	0.699583	0.687320	0.705856	0.692138	0.699529	-0.316324	0.709477
total_amt', Period2021-07_M	0.478910	0.847710	0.839360	0.841998	0.850282	0.855812	0.850500	0.858493	0.863354	0.849302	0.848022	0.844699	0.857952	0.837513	0.836509	0.846562	0.838280	0.832271	0.797548	0.835033	0.832145	0.824686	0.815409	0.816836	0.863391	0.796879	0.776078	0.833204	0.808775	0.800745	0.840568	1.000000	0.772714	0.801728	0.845850	0.774571	0.861364	0.675025	0.647721	0.630640	0.650572	0.666436	0.675242	0.674190	0.681045	0.680159	0.641775	0.643938	0.496206	0.858029	0.857599	0.856516	0.858813	0.859492	0.866968	0.867560	0.868081	0.864561	0.862307	0.868110	0.870231	0.865490	0.860657	0.864568	0.864139	0.868226	0.869002	0.870599	0.865589	0.873158	0.867138	0.869573	0.877406	0.860408	0.857013	0.869511	0.867627	0.868917	0.872879	0.889547	0.867957	0.871057	0.873343	0.858957	0.876728	0.715777	0.687885	0.682778	0.684271	0.695373	0.691893	0.689911	0.690176	0.688407	0.688227	0.680297	0.691764	-0.302711	0.722674
total_amt', Period2021-08_M	0.475206	0.778866	0.790242	0.788268	0.785117	0.792227	0.794651	0.787473	0.789950	0.780298	0.790080	0.778445	0.782097	0.778458	0.766017	0.788282	0.766574	0.775290	0.749587	0.781385	0.776504	0.768973	0.756906	0.746658	0.790196	0.760450	0.743634	0.771792	0.762056	0.740192	0.781678	0.772714	1.000000	0.741208	0.773351	0.715888	0.812595	0.629066	0.594217	0.575848	0.594476	0.599730	0.623365	0.616294	0.632242	0.638999	0.595940	0.598759	0.484118	0.803068	0.815242	0.814943	0.813133	0.812509	0.818008	0.814901	0.815709	0.813548	0.811621	0.808976	0.813579	0.827901	0.809988	0.813509	0.808143	0.810175	0.821607	0.817686	0.815161	0.819689	0.808631	0.812972	0.821615	0.812190	0.802824	0.817210	0.820722	0.815768	0.815288	0.814668	0.839336	0.815995	0.814881	0.809838	0.822088	0.673349	0.648396	0.641121	0.638037	0.646214	0.649635	0.644750	0.644037	0.641402	0.648356	0.633065	0.640839	-0.287198	0.651812
total_amt', Period2021-09_M	0.483292	0.797004	0.791644	0.807852	0.794618	0.808272	0.814241	0.814664	0.810299	0.799661	0.805233	0.799951	0.808274	0.805156	0.786983	0.801736	0.782726	0.795886	0.745775	0.783119	0.774239	0.778712	0.780611	0.743482	0.806318	0.754640	0.722422	0.775037	0.761180	0.753670	0.802595	0.801728	0.741208	1.000000	0.765884	0.738678	0.805963	0.643848	0.608903	0.592061	0.620547	0.613804	0.633848	0.623896	0.640626	0.640622	0.614235	0.599072	0.501903	0.796010	0.793907	0.807301	0.795793	0.800381	0.812641	0.807560	0.803491	0.802012	0.800364	0.813086	0.808460	0.809180	0.801170	0.806146	0.801620	0.812169	0.810846	0.805930	0.800896	0.809093	0.812074	0.804639	0.809342	0.800130	0.798934	0.808183	0.800815	0.803747	0.811085	0.809659	0.813269	0.835917	0.809729	0.803070	0.812219	0.671201	0.632295	0.632333	0.631868	0.635526	0.638216	0.637049	0.637886	0.628512	0.639768	0.632765	0.635479	-0.275483	0.662267
total_amt', Period2021-10_M	0.476297	0.834971	0.824704	0.843001	0.845026	0.844530	0.843420	0.851908	0.851879	0.844426	0.837020	0.835893	0.839210	0.828551	0.824944	0.836418	0.832518	0.824940	0.794994	0.827048	0.820864	0.806085	0.823262	0.800522	0.836247	0.792968	0.770963	0.830704	0.810708	0.786160	0.830789	0.845850	0.773351	0.765884	1.000000	0.759562	0.844598	0.659359	0.649688	0.614980	0.647098	0.650972	0.659179	0.656405	0.665522	0.682014	0.642610	0.625860	0.483651	0.839599	0.844295	0.848654	0.848252	0.849656	0.845425	0.852940	0.850754	0.851162	0.844691	0.849273	0.852317	0.852969	0.843693	0.847782	0.853793	0.854646	0.858662	0.855844	0.850594	0.854147	0.851381	0.856394	0.860173	0.851020	0.839201	0.854586	0.851739	0.853495	0.856025	0.853465	0.851245	0.848588	0.880462	0.849140	0.858108	0.703209	0.674024	0.660750	0.668346	0.677952	0.677476	0.672796	0.670578	0.672335	0.675826	0.664605	0.675287	-0.292653	0.709599
total_amt', Period2021-11_M	0.446306	0.789355	0.786317	0.787829	0.782626	0.797268	0.791439	0.796234	0.793491	0.787031	0.788109	0.783851	0.799571	0.774327	0.790430	0.785224	0.773285	0.776832	0.744705	0.784321	0.762720	0.740755	0.768379	0.730007	0.799932	0.759878	0.718047	0.770031	0.759477	0.737556	0.774766	0.774571	0.715888	0.738678	0.759562	1.000000	0.806195	0.628101	0.606975	0.590814	0.606378	0.623140	0.632374	0.634487	0.639084	0.641317	0.611075	0.609270	0.462200	0.797547	0.802583	0.797377	0.796717	0.798538	0.801744	0.803974	0.800960	0.802815	0.805998	0.804020	0.806325	0.797452	0.803746	0.803126	0.806219	0.802144	0.806326	0.803352	0.797764	0.800672	0.801389	0.800262	0.809490	0.801373	0.800263	0.804833	0.803776	0.806309	0.800385	0.805457	0.808275	0.809525	0.803156	0.830238	0.812390	0.670213	0.642693	0.634674	0.636572	0.648841	0.648653	0.641581	0.645226	0.646185	0.645588	0.640701	0.644104	-0.277398	0.666978
total_amt', Period2021-12_M	0.471941	0.866196	0.869827	0.878504	0.876798	0.880724	0.886241	0.884223	0.891064	0.876235	0.878820	0.870674	0.888657	0.867870	0.868080	0.869897	0.859573	0.859753	0.829917	0.856908	0.856917	0.838687	0.840438	0.837022	0.883340	0.828306	0.815118	0.851767	0.839062	0.832624	0.867800	0.861364	0.812595	0.805963	0.844598	0.806195	1.000000	0.695607	0.656057	0.634426	0.661567	0.682089	0.690018	0.693509	0.696125	0.697670	0.671312	0.658042	0.498203	0.882349	0.887027	0.891025	0.890029	0.890360	0.897324	0.894151	0.898391	0.891175	0.895028	0.895872	0.897528	0.892282	0.891653	0.893022	0.887143	0.891476	0.901088	0.894689	0.895363	0.896496	0.888408	0.896863	0.902532	0.889742	0.886847	0.895471	0.892859	0.893501	0.900457	0.893634	0.898360	0.895177	0.896317	0.889986	0.915550	0.734516	0.700906	0.695031	0.697487	0.706582	0.707091	0.705079	0.701228	0.699030	0.706657	0.695593	0.701500	-0.318287	0.731005
total_amt', Period2022-01_M	0.425631	0.738596	0.720941	0.744890	0.754006	0.747312	0.749527	0.752446	0.748756	0.748833	0.746373	0.751966	0.761777	0.739898	0.737732	0.752503	0.674635	0.657608	0.623147	0.659585	0.658404	0.671684	0.640238	0.643298	0.670343	0.653574	0.606273	0.660021	0.627065	0.645610	0.675497	0.675025	0.629066	0.643848	0.659359	0.628101	0.695607	1.000000	0.883676	0.881338	0.896079	0.894339	0.855823	0.857600	0.858190	0.865026	0.851335	0.823180	0.368353	0.639137	0.632641	0.647443	0.648542	0.644262	0.649411	0.652859	0.647894	0.648796	0.649143	0.656003	0.654720	0.653893	0.654266	0.647110	0.643662	0.647402	0.657238	0.650441	0.655151	0.661767	0.636302	0.654463	0.657859	0.654801	0.633372	0.652921	0.643644	0.653296	0.659509	0.654579	0.651456	0.658455	0.649211	0.644061	0.650143	0.870999	0.841274	0.847472	0.851319	0.851104	0.851914	0.850658	0.849944	0.845167	0.854856	0.849208	0.850431	-0.414632	0.881193
total_amt', Period2022-02_M	0.423659	0.723252	0.714472	0.729361	0.736801	0.735611	0.737941	0.739745	0.734571	0.734449	0.727265	0.737661	0.751094	0.727243	0.723896	0.733344	0.644672	0.632602	0.606901	0.637151	0.628213	0.648304	0.635065	0.617644	0.645004	0.620659	0.574141	0.635524	0.587097	0.608060	0.632633	0.647721	0.594217	0.608903	0.649688	0.606975	0.656057	0.883676	1.000000	0.900810	0.904186	0.898019	0.858006	0.859814	0.856983	0.879038	0.845883	0.824174	0.350528	0.594229	0.600171	0.604270	0.610641	0.607653	0.608878	0.612684	0.604810	0.607961	0.609502	0.618120	0.612870	0.613016	0.612110	0.605830	0.598896	0.607639	0.614022	0.614259	0.612405	0.623802	0.594838	0.614687	0.617508	0.606810	0.590488	0.606438	0.596235	0.614028	0.614823	0.611080	0.606073	0.617068	0.610966	0.611118	0.606469	0.825256	0.871897	0.842511	0.840038	0.839816	0.846499	0.843304	0.843900	0.843595	0.844115	0.845864	0.845610	-0.410968	0.882408
total_amt', Period2022-03_M	0.413413	0.710342	0.697890	0.718262	0.723432	0.716229	0.718949	0.725418	0.710101	0.715830	0.713202	0.714785	0.728168	0.707702	0.703950	0.718754	0.631092	0.603902	0.585160	0.614829	0.614694	0.621175	0.598678	0.596428	0.618703	0.593945	0.561752	0.627351	0.566314	0.606820	0.613937	0.630640	0.575848	0.592061	0.614980	0.590814	0.634426	0.881338	0.900810	1.000000	0.903376	0.895180	0.847539	0.848856	0.852346	0.858093	0.839957	0.826637	0.337983	0.578121	0.581321	0.585532	0.586439	0.586210	0.589333	0.595487	0.580015	0.585248	0.590743	0.591763	0.591939	0.595720	0.591221	0.587687	0.582942	0.586049	0.594395	0.588250	0.593187	0.597142	0.574834	0.591694	0.595496	0.587042	0.568729	0.590446	0.573805	0.598556	0.593725	0.589418	0.588579	0.599657	0.591634	0.586675	0.585431	0.813924	0.831407	0.850891	0.829609	0.833267	0.835346	0.833152	0.833228	0.828886	0.832791	0.833495	0.836847	-0.401775	0.875140

	mae	mse	rmse
Lasso_FEATURE1_Train	2278.114357	1.223520e+07	3497.885577
Lasso_FEATURE1_Val	2123.981346	9.719629e+06	3117.631893

	mae	mse	rmse
Lasso_FEATURE2_Train	2092.325287	1.030345e+07	3209.898411
Lasso_FEATURE2_Val	2117.264295	9.286441e+06	3047.366207

	mae	mse	rmse
Lasso_FEATURE3_Train	2279.940306	1.223561e+07	3497.943503
Lasso_FEATURE3_Val	2127.655356	9.759305e+06	3123.988600

	mae	mse	rmse
Ridge_Train	2061.966576	9.326546e+06	3053.939442
Ridge_Val	2211.667197	9.930921e+06	3151.336341

	mae	mse	rmse
Ridge_FEATURE1_Train	2274.841596	1.225304e+07	3500.433978
Ridge_FEATURE1_Val	2108.951082	9.600463e+06	3098.461357

	mae	mse	rmse
Ridge_FEATURE2_Train	2084.101832	1.031979e+07	3212.443623
Ridge_FEATURE2_Val	2102.691899	9.118768e+06	3019.729731

	mae	mse	rmse
Ridge_FEATURE3_Train	2278.747159	1.223434e+07	3497.762131
Ridge_FEATURE3_Val	2124.893956	9.739202e+06	3120.769408

	mae	mse	rmse
Elastic_Train	2284.880425	1.238910e+07	3519.815887
Elastic_Val	2073.707562	8.579011e+06	2928.994854

	mae	mse	rmse
Elastic_FEATURE1_Train	2469.341627	1.406453e+07	3750.270443
Elastic_FEATURE1_Val	2185.184604	9.342266e+06	3056.512135

	mae	mse	rmse
Elastic_FEATURE2_Train	2321.397873	1.289433e+07	3590.867219
Elastic_FEATURE2_Val	2109.088513	8.697749e+06	2949.194714

	mae	mse	rmse
Elastic_FEATURE3_Train	2279.672369	1.223548e+07	3497.925509
Elastic_FEATURE3_Val	2126.979548	9.753365e+06	3123.037799

	mae	mse	rmse
Dtregressor_Train	0.000000	0.000000e+00	0.000000
Dtregressor_Val	3022.997923	1.981871e+07	4451.821535

	mae	mse	rmse
Dtregressor_FEATURE1_Train	0.000000	0.000000e+00	0.000000
Dtregressor_FEATURE1_Val	3142.906175	2.105998e+07	4589.114999

Regression Analysis¶

Customer data¶

Transaction data¶

Data Dictionary¶

Convert unix_time to trans_month_year, and quarter¶

We will filter only is_fraud = 0, since we don't want to have any frualent transaction¶

Monthly Spending¶

We will group the data by acct_num, and trans_month_year and find the total amount of spending per month, total number of transaction, and the most frequent category.¶

Correlation Plot¶

Splitting the Data¶

Peform One-hot Encoding and Frequency Encoding¶

One-hot Encoding¶

- gender¶

Frequency Encoding¶

Data Standarization (Standard Scalling)¶

I. Multivariate Linear Regression¶

Baseline model¶

Baseline Train dataset¶

Baseline Test dataset¶

Multilinear Function¶

1. Multi Linear Regression with All Feature¶

2. Feature Engineering 1 (Correlation >= 0.5)¶

3. Feature Engineering 2 (Correlation >= 0.7)¶

4. Feature Engineering 3 (Correlation >= 0.8)¶

II. Lasso Model¶

Lasso Function¶

1. Lasso Regression with All Features¶

2. Lasso Regression Feature Engineering 1 (Correlation >= 0.5)¶

3. Lasso Regression Feature Engineering 2 (Correlation >= 0.7)¶

4. Lasso Regression Feature Engineering 3 (Correlation >= 0.8)¶

III. Ridge Model¶

Ridge Function¶

1. Ridge Regression with All Features¶

2. Ridge Regression Feature Engineering 1 (Correlation >= 0.5)¶

3. Ridge Regression Feature Engineering 2 (Correlation >= 0.7)¶

4. Ridge Regression Feature Engineering 3 (Correlation >= 0.8)¶

IV. ElasticNet¶

ElasticNet Function¶

1. ElasticNet with All Features¶

2. ElasticNet Feature Engineering 1 (Correlation >= 0.5)¶

3. ElasticNet Feature Engineering 1 (Correlation >= 0.7)¶

4. ElasticNet Feature Engineering 1 (Correlation >= 0.8)¶

V. Decision Tree Regression¶

Decision Tree Function (Default Hyperparameter)¶

1. Decision Tree Regression with All Features¶

2. Decision Tree Regression Feature Engineering 1 (Correlation >= 0.5)¶

3. Decision Tree Regression Feature Engineering 2 (Correlation >= 0.7)¶

4. Decision Tree Regression Feature Engineering 3 (Correlation >= 0.8)¶

Hyperparameter Tuning¶

Reduce Overfitting with max_depth (default = None)¶

max_depth = 5 appears to be the best choice¶

Reduce Overfitting with min_samples_split (max_depth=10)¶

Reduce Overfitting with min_samples_leaf (max_depth=10, min_samples_split=10)¶

min_samples_leaf = 2 appears to be the best choice¶

Reduce Overfitting with max_features (max_depth=10, min_samples_split=10, min_samples_leaf=20)¶

max_features = 10 appears to be the best choice¶

Reduce Overfitting with criterion (max_depth=10, min_samples_split=10, min_samples_leaf=20, max_features=10)¶

After Hyperparameter tuning¶

1. Decision Tree Regression with All Features¶

2. Decision Tree Regression with Feature Enginerring 1 (Correlation > 0.5)¶

3. Decision Tree Regression with Feature Enginerring 1 (Correlation > 0.7)¶

4. Decision Tree Regression with Feature Enginerring 1 (Correlation > 0.8)¶

VI. Random Forest Regression¶

Random Forest Function (Default Hyperparameter)¶

1. Random Forest Regressor with All Features¶

2. Random Forest Regressor with Feature Enginerring 1 (Correlation > 0.5)¶

3. Random Forest Regressor with Feature Enginerring 2 (Correlation > 0.7)¶

4. Random Forest Regressor with Feature Enginerring 3 (Correlation > 0.8)¶

Hyperparameter Tuning¶

Reduce Overfitting with n_estimators¶

Reduce Overfitting with max_depth¶

Reduce Overfitting with min_samples_split¶

Reduce Overfitting with min_samples_leaf¶

Reduce Overfitting with max_features¶

After Hyperparameter Tuning¶

1. Random Forest Regressor with All Features¶

2. Random Forest Regressor with Feature Engineering 1 (Correlation > 0.5)¶

3. Random Forest Regressor with Feature Engineering 2 (Correlation > 0.7)¶

4. Random Forest Regressor with Feature Engineering 3 (Correlation > 0.8)¶

VII. XGBoost¶

	mae	mse	rmse
Dtregressor_FEATURE2_Train	0.00000	0.000000e+00	0.000000
Dtregressor_FEATURE2_Val	3379.59929	2.756409e+07	5250.151896

	mae	mse	rmse
Dtregressor_FEATURE3_Train	0.000000	0.000000e+00	0.0000
Dtregressor_FEATURE3_Val	3090.758525	2.071248e+07	4551.0961

	train_mae	test_mae	train_mse	test_mse	train_rmse	test_rmse
2.0	3815.480925	3614.774442	2.645389e+07	2.241880e+07	5143.334947	4734.849732
5.0	2017.879079	2632.876525	8.616914e+06	1.638042e+07	2935.458046	4047.273239
10.0	432.658774	3125.795647	6.059501e+05	2.398058e+07	778.427956	4896.996807
20.0	5.152083	3292.034456	1.172666e+03	2.500349e+07	34.244207	5000.348965
50.0	0.000000	3022.997923	0.000000e+00	1.981871e+07	0.000000	4451.821535
100.0	0.000000	3022.997923	0.000000e+00	1.981871e+07	0.000000	4451.821535
150.0	0.000000	3022.997923	0.000000e+00	1.981871e+07	0.000000	4451.821535
200.0	0.000000	3022.997923	0.000000e+00	1.981871e+07	0.000000	4451.821535
NaN	0.000000	3022.997923	0.000000e+00	1.981871e+07	0.000000	4451.821535

	train_mae	test_mae	train_mse	test_mse	train_rmse	test_rmse
2	2434.628170	2495.077908	1.234958e+07	1.434912e+07	3514.197533	3788.023115
5	2400.117670	2497.152084	1.252384e+07	1.462245e+07	3538.903512	3823.930808
10	2529.828746	2693.498737	1.408535e+07	1.772781e+07	3753.045990	4210.440371
20	2542.741510	2787.395009	1.481632e+07	1.640833e+07	3849.197790	4050.719254
50	3023.045614	2977.038460	1.974248e+07	1.712419e+07	4443.251073	4138.138037
100	4096.456639	3858.048355	3.413148e+07	3.090315e+07	5842.215653	5559.060013
150	4303.294377	4110.614686	3.558026e+07	3.377878e+07	5964.918713	5811.951725
200	5393.094725	4675.050604	4.920576e+07	3.827844e+07	7014.681598	6186.957172

	train_mae	test_mae	train_mse	test_mse	train_rmse	test_rmse
1	4264.657260	4616.025908	3.212019e+07	3.590294e+07	5667.467929	5991.906389
2	3881.229772	4051.035539	2.541137e+07	3.018227e+07	5040.968720	5493.839657
3	3426.687014	3721.874845	2.364337e+07	2.306265e+07	4862.445246	4802.358837
4	3097.223558	3580.844608	1.866593e+07	2.397298e+07	4320.408298	4896.220703
5	3202.852552	3238.518236	2.015210e+07	2.089132e+07	4489.109075	4570.702049
6	3106.749747	3474.954972	1.910198e+07	2.435943e+07	4370.580762	4935.527600
7	2728.941066	2887.399486	1.673508e+07	1.758785e+07	4090.853564	4193.786896
8	2666.172170	3081.998005	1.515382e+07	1.999276e+07	3892.790373	4471.326484
9	2664.665506	3068.606964	1.523465e+07	1.875990e+07	3903.159341	4331.269661
10	2415.864738	2343.437093	1.281677e+07	1.175229e+07	3580.051743	3428.161970
11	2654.738472	2897.205908	1.495893e+07	1.681862e+07	3867.677397	4101.051515
12	2675.450560	3075.612277	1.679244e+07	1.990135e+07	4097.858027	4461.092723
13	2484.843948	2889.408818	1.352989e+07	1.920853e+07	3678.300071	4382.753376
14	2595.096972	3068.558237	1.430120e+07	1.838980e+07	3781.693126	4288.333164
15	2718.399858	3016.266256	1.549448e+07	1.918380e+07	3936.303111	4379.931101
16	2582.769468	2934.521535	1.614190e+07	1.652437e+07	4017.697807	4065.017308
17	2530.412028	2864.433139	1.385684e+07	1.625640e+07	3722.477498	4031.922083
18	2549.521050	2871.871144	1.324068e+07	1.791743e+07	3638.775045	4232.898402
19	2685.614858	2787.644288	1.566936e+07	1.919058e+07	3958.454428	4380.705239
20	2690.517661	2755.131712	1.593639e+07	1.592006e+07	3992.040610	3989.994524
21	2713.216617	2790.841853	1.680501e+07	1.661129e+07	4099.390921	4075.695516
22	2519.717968	2625.160921	1.336965e+07	1.485764e+07	3656.452782	3854.561401
23	2632.505031	2772.088734	1.505643e+07	1.744229e+07	3880.261976	4176.397070
24	2664.922298	3066.453710	1.623056e+07	1.739398e+07	4028.716796	4170.609643
25	2598.182466	2894.304121	1.510566e+07	1.545932e+07	3886.599621	3931.834754
26	2486.253606	2802.219441	1.275504e+07	1.889001e+07	3571.420374	4346.264177
27	2476.739796	2941.197604	1.267193e+07	2.079016e+07	3559.765707	4559.622518
28	2747.288799	2951.437696	1.719211e+07	1.743517e+07	4146.337260	4175.543852
29	2639.839210	2920.397189	1.610752e+07	1.798974e+07	4013.417492	4241.431158
30	2635.788221	2859.073720	1.488086e+07	1.725833e+07	3857.572241	4154.314315
31	2768.473489	2814.408148	1.718205e+07	1.580990e+07	4145.123584	3976.166184
32	2429.230821	2776.043621	1.260990e+07	1.723332e+07	3551.041823	4151.303390
33	2464.360038	2912.959982	1.308792e+07	2.071590e+07	3617.723629	4551.472378
34	2608.391222	3237.114353	1.397910e+07	2.308207e+07	3738.863757	4804.380732
35	2510.333978	2790.691469	1.327830e+07	1.607366e+07	3643.940532	4009.197502
36	2489.379869	2396.316350	1.250927e+07	1.174200e+07	3536.844009	3426.660796
37	2556.300489	2602.215159	1.308516e+07	1.471822e+07	3617.341451	3836.433054
38	2429.550738	2956.865052	1.267424e+07	2.228661e+07	3560.089871	4720.870151
39	2479.682919	2686.939230	1.285882e+07	1.576122e+07	3585.919783	3970.039915

	train_mae	test_mae	train_mse	test_mse	train_rmse	test_rmse
absolute_error	2538.360879	2528.292131	1.766422e+07	1.374484e+07	4202.881995	3707.403884
squared_error	2428.632887	2377.058551	1.302080e+07	1.166857e+07	3608.435026	3415.929063
friedman_mse	2428.632887	2377.058551	1.302080e+07	1.166857e+07	3608.435026	3415.929063
poisson	2696.912025	2604.426164	1.551771e+07	1.462207e+07	3939.252978	3823.881632

	mae	mse	rmse
DT_Tune_Train	2428.632887	1.302080e+07	3608.435026
DT_Tune_Val	2377.058551	1.166857e+07	3415.929063

	mae	mse	rmse
DT_Tune_FEATURE1_Train	2634.547381	1.511255e+07	3887.486135
DT_Tune_FEATURE1_Val	2843.669581	1.846317e+07	4296.879298

	mae	mse	rmse
DT_Tune_FEATURE2_Train	2640.609970	1.566922e+07	3958.435982
DT_Tune_FEATURE2_Val	2532.673206	1.454901e+07	3814.316998

	mae	mse	rmse
DT_Tune_FEATURE3_Train	2634.547381	1.511255e+07	3887.486135
DT_Tune_FEATURE3_Val	2855.303550	1.849346e+07	4300.402255